Compare commits
365
Commits
No files matched your search
@@ -0,0 +1,160 @@
|
|||||||
|
# CouchDB erlangCookie Fix - Implementation Guide
|
||||||
|
|
||||||
|
## Summary
|
||||||
|
|
||||||
|
**Problem**: CouchDB deployment fails because `erlangCookie` is missing from the ExternalSecret configuration.
|
||||||
|
|
||||||
|
**Decision**: Externalize `erlangCookie` to 1Password (pragmatic approach)
|
||||||
|
|
||||||
|
**Rationale**:
|
||||||
|
- ExternalSecret architecture requires ownership of the entire secret
|
||||||
|
- Mixing externalized and chart-generated fields in the same secret is not supported
|
||||||
|
- Single-node deployment makes erlangCookie rotation unnecessary
|
||||||
|
- This is an acceptable deviation from the pure Harbor pattern given the architectural constraints
|
||||||
|
|
||||||
|
## Implementation Steps
|
||||||
|
|
||||||
|
### 1. Generate erlangCookie Value
|
||||||
|
|
||||||
|
```bash
|
||||||
|
openssl rand -hex 20
|
||||||
|
```
|
||||||
|
|
||||||
|
Example output: `f4e3c2b1a9d8e7f6c5b4a3d2e1f0a9b8c7d6e5f4`
|
||||||
|
|
||||||
|
### 2. Add to 1Password
|
||||||
|
|
||||||
|
- **Vault**: `mk-labs`
|
||||||
|
- **Item**: `couchdb`
|
||||||
|
- **Field Name**: `erlang-cookie`
|
||||||
|
- **Field Type**: password (concealed)
|
||||||
|
- **Value**: `<paste generated value from step 1>`
|
||||||
|
|
||||||
|
### 3. Update ExternalSecret Configuration
|
||||||
|
|
||||||
|
File: `cluster/applications/couchdb/externalsecret.yaml`
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
apiVersion: external-secrets.io/v1beta1
|
||||||
|
kind: ExternalSecret
|
||||||
|
metadata:
|
||||||
|
name: couchdb-credentials
|
||||||
|
namespace: couchdb
|
||||||
|
labels:
|
||||||
|
app.kubernetes.io/name: couchdb
|
||||||
|
app.kubernetes.io/part-of: mk-labs
|
||||||
|
spec:
|
||||||
|
refreshInterval: 1h
|
||||||
|
secretStoreRef:
|
||||||
|
kind: ClusterSecretStore
|
||||||
|
name: onepassword-connect
|
||||||
|
target:
|
||||||
|
name: couchdb-admin
|
||||||
|
creationPolicy: Owner
|
||||||
|
template:
|
||||||
|
engineVersion: v2
|
||||||
|
data:
|
||||||
|
adminUsername: "admin"
|
||||||
|
adminPassword: "{{ .adminPassword }}"
|
||||||
|
cookieAuthSecret: "{{ .cookieAuthSecret }}"
|
||||||
|
erlangCookie: "{{ .erlangCookie }}" # ← ADD THIS LINE
|
||||||
|
data:
|
||||||
|
- secretKey: adminPassword
|
||||||
|
remoteRef:
|
||||||
|
key: couchdb
|
||||||
|
property: admin-password
|
||||||
|
- secretKey: cookieAuthSecret
|
||||||
|
remoteRef:
|
||||||
|
key: couchdb
|
||||||
|
property: cookie-auth-secret
|
||||||
|
- secretKey: erlangCookie # ← ADD THIS BLOCK
|
||||||
|
remoteRef:
|
||||||
|
key: couchdb
|
||||||
|
property: erlang-cookie
|
||||||
|
```
|
||||||
|
|
||||||
|
### 4. Update values.yaml Documentation (Optional)
|
||||||
|
|
||||||
|
File: `cluster/applications/couchdb/values.yaml`
|
||||||
|
|
||||||
|
Update the comment block at line 9-10:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
# Admin credentials managed via ExternalSecret
|
||||||
|
# See externalsecret.yaml for 1Password integration
|
||||||
|
#
|
||||||
|
# NOTE: erlangCookie is externalized to 1Password for architectural
|
||||||
|
# simplicity (ExternalSecret ownership model). In a pure Harbor pattern,
|
||||||
|
# this would be chart-generated, but single-node deployment makes this
|
||||||
|
# acceptable. The erlangCookie is treated as an immutable infrastructure
|
||||||
|
# secret (generate once, never rotate).
|
||||||
|
createAdminSecret: false
|
||||||
|
extraSecretName: "couchdb-admin"
|
||||||
|
```
|
||||||
|
|
||||||
|
### 5. Commit and Push
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd ~/git/homelab
|
||||||
|
git add cluster/applications/couchdb/externalsecret.yaml
|
||||||
|
git add cluster/applications/couchdb/values.yaml # if modified
|
||||||
|
git commit -m "fix(couchdb): add erlangCookie to ExternalSecret from 1Password"
|
||||||
|
git push origin main
|
||||||
|
```
|
||||||
|
|
||||||
|
### 6. Verify Deployment
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Watch ExternalSecret sync
|
||||||
|
kubectl get externalsecret -n couchdb couchdb-credentials -w
|
||||||
|
# Wait for: SecretSynced
|
||||||
|
|
||||||
|
# Verify secret created with all four keys
|
||||||
|
kubectl get secret -n couchdb couchdb-admin -o yaml
|
||||||
|
# Should contain: adminUsername, adminPassword, cookieAuthSecret, erlangCookie
|
||||||
|
|
||||||
|
# Watch ArgoCD sync
|
||||||
|
kubectl get application -n argocd couchdb -w
|
||||||
|
# Wait for: Healthy/Synced
|
||||||
|
|
||||||
|
# Watch pod startup
|
||||||
|
kubectl get pods -n couchdb -w
|
||||||
|
# Wait for: Running
|
||||||
|
|
||||||
|
# Test CouchDB access
|
||||||
|
kubectl port-forward -n couchdb svc/couchdb-svc-couchdb 5984:5984 &
|
||||||
|
curl http://localhost:5984/
|
||||||
|
# Expected: {"couchdb":"Welcome","version":"3.5.1"}
|
||||||
|
```
|
||||||
|
|
||||||
|
## Why Not Follow Harbor Pattern Exactly?
|
||||||
|
|
||||||
|
**Harbor Pattern**: Only user-facing credentials externalized, internal secrets chart-generated.
|
||||||
|
|
||||||
|
**CouchDB Constraint**: ExternalSecret uses `creationPolicy: Owner`, which takes full ownership of the target secret. This prevents the Helm chart from adding auto-generated fields to the same secret.
|
||||||
|
|
||||||
|
**Options Considered**:
|
||||||
|
1. ✅ **Externalize erlangCookie** (SELECTED) - Works with current architecture
|
||||||
|
2. ❌ Chart auto-generation - Conflicts with ExternalSecret ownership
|
||||||
|
3. ❌ Dual-secret approach - Requires Helm chart customization
|
||||||
|
4. ❌ Disable ExternalSecret - Loses 1Password integration for admin password
|
||||||
|
|
||||||
|
**Decision**: Pragmatic approach wins. erlangCookie is treated as an infrastructure secret (generate once, never rotate), which is acceptable for a single-node deployment.
|
||||||
|
|
||||||
|
## Secret Classification
|
||||||
|
|
||||||
|
| Secret | Type | 1Password? | Rationale |
|
||||||
|
|------------------|---------------|------------|------------------------------------|
|
||||||
|
| adminUsername | User-facing | No* | Static value, hardcoded in template |
|
||||||
|
| adminPassword | User-facing | ✅ YES | User login credential |
|
||||||
|
| cookieAuthSecret | Gray area | ✅ YES | Session security, periodic rotation |
|
||||||
|
| erlangCookie | Internal | ✅ YES** | Architectural constraint |
|
||||||
|
|
||||||
|
\* Hardcoded in ExternalSecret template (not fetched from 1Password)
|
||||||
|
\*\* Pragmatic deviation from Harbor pattern due to ExternalSecret architecture
|
||||||
|
|
||||||
|
## References
|
||||||
|
|
||||||
|
- Full analysis: `/home/hermes/couchdb-erlangcookie-analysis.txt`
|
||||||
|
- Harbor pattern: `/home/hermes/harbor-simplification-complete.txt`
|
||||||
|
- CouchDB Helm chart: `apache/couchdb` v4.6.3
|
||||||
@@ -0,0 +1,702 @@
|
|||||||
|
# Account Dossier Interactive Dashboard — Design Document
|
||||||
|
|
||||||
|
**Version:** 0.1 (MVP)
|
||||||
|
**Author:** Claude
|
||||||
|
**Date:** 2026-10-07
|
||||||
|
**Status:** Design Review (Pre-Prototype)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 1. Overview & Purpose
|
||||||
|
|
||||||
|
**What:** Interactive HTML/React dashboard that surfaces account intelligence for a single Pure Storage customer or prospect. Provides a "10,000 ft view" with drill-down to ground-level detail.
|
||||||
|
|
||||||
|
**Why:** SEs need to move quickly from account snapshot → discovery prep → conversation context without context-switching between Sheets, notes, and browser tabs. One dashboard per customer becomes the source of reference for that account.
|
||||||
|
|
||||||
|
**MVP Scope:** The 10 essential questions (List 1 + List 2 from account intelligence framework)
|
||||||
|
|
||||||
|
**Future Scope:** Relationships, opportunities, financial modeling, industry trends, sentiment analysis, timeline views
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 2. User Personas & Use Cases
|
||||||
|
|
||||||
|
### Primary User
|
||||||
|
**Ryan** (You, Enterprise SE)
|
||||||
|
- Prepping for discovery calls
|
||||||
|
- Hunting for competitive displacement opportunities
|
||||||
|
- Planning expansion/renewal strategy
|
||||||
|
- Sharing account context with team (future)
|
||||||
|
|
||||||
|
### Use Cases (in priority order, all equally weighted for MVP)
|
||||||
|
|
||||||
|
| Use Case | What They Need | Where Dashboard Helps |
|
||||||
|
|----------|---|---|
|
||||||
|
| **Pre-call Prep (15 min before discovery)** | Quick account snapshot + key metrics + conversation hooks | Overview pane + drill-down to specific List items; see what changed since last call |
|
||||||
|
| **Competitive Displacement Hunting** | Incumbent vendors + footprint + gaps + consolidation leverage | List 2 drill-down showing Pure coverage % + high-value data not on Pure; see EMC systems aging |
|
||||||
|
| **Expansion/Renewal Planning** | Growth trajectory + budget cycle + stakeholder sentiment + upcoming initiatives | Opportunity tab (future) + timeline + stakeholder relationships; see refresh window + budget headroom |
|
||||||
|
|
||||||
|
### Secondary User (Future)
|
||||||
|
**Account team** (Sales, Solution Architect, Customer Success)
|
||||||
|
- Read-only view of account summary
|
||||||
|
- Understand strategic context before customer calls
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 3. Architecture Overview
|
||||||
|
|
||||||
|
### 3.1 Data Flow Diagram
|
||||||
|
|
||||||
|
```
|
||||||
|
┌─────────────────────────────────────────────────────────────┐
|
||||||
|
│ Per-Customer Data Sources (DRY: No Duplication) │
|
||||||
|
├─────────────────────────────────────────────────────────────┤
|
||||||
|
│ │
|
||||||
|
│ 📊 Google Sheet (Structured Data) │
|
||||||
|
│ ├─ Account tab (List 1 metrics) │
|
||||||
|
│ ├─ Pure-Deployment tab (List 2 metrics) │
|
||||||
|
│ ├─ Relationships tab (Contacts, sentiment, history) │
|
||||||
|
│ ├─ Interactions tab (Call/email log with sentiment) │
|
||||||
|
│ ├─ Financials tab (ARR, contracts, opportunities) │
|
||||||
|
│ ├─ Industry-Trends tab (Curated insights) │
|
||||||
|
│ └─ Metadata tab (Sync status, ownership, sharing) │
|
||||||
|
│ │
|
||||||
|
│ 📝 Obsidian Markdown File (Unstructured Context) │
|
||||||
|
│ ├─ Discovery notes (narrative, conversation context) │
|
||||||
|
│ ├─ Strategy (account themes, expansion hooks) │
|
||||||
|
│ ├─ Relationship notes (person-by-person context) │
|
||||||
|
│ └─ Internal flags (competitive threats, risks) │
|
||||||
|
│ │
|
||||||
|
└─────────────────────────────────────────────────────────────┘
|
||||||
|
↓
|
||||||
|
(via API or manual sync)
|
||||||
|
↓
|
||||||
|
┌─────────────────────────────────────────────────────────────┐
|
||||||
|
│ Interactive Dashboard (HTML/React Artifact) │
|
||||||
|
│ Reads from both sources, displays in 3-pane layout │
|
||||||
|
│ No data copying; all reads from source │
|
||||||
|
└─────────────────────────────────────────────────────────────┘
|
||||||
|
↓
|
||||||
|
(displayed to user)
|
||||||
|
↓
|
||||||
|
┌─────────────────────────────────────────────────────────────┐
|
||||||
|
│ User Actions: │
|
||||||
|
│ • View account snapshot │
|
||||||
|
│ • Drill into List 1 / List 2 metrics │
|
||||||
|
│ • Check stakeholder sentiment │
|
||||||
|
│ • Review opportunity pipeline │
|
||||||
|
│ • Log new interaction │
|
||||||
|
│ • Open full Sheets / Obsidian for detailed editing │
|
||||||
|
└─────────────────────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 4. UI/UX Design
|
||||||
|
|
||||||
|
### 4.1 Layout: 3-Pane Architecture
|
||||||
|
|
||||||
|
```
|
||||||
|
┌──────────────────────────────────────────────────────────────────────┐
|
||||||
|
│ HEADER: Account Name | Status | Vertical | Location | [Share] [Edit] │
|
||||||
|
├─────────────────────────────────────────────────────────────────────┤
|
||||||
|
│ │
|
||||||
|
│ LEFT PANE │ CENTER PANE │ RIGHT PANE │
|
||||||
|
│ (Overview) │ (Details & Drill-down) │ (Context) │
|
||||||
|
│ │ │ │
|
||||||
|
│ ┌─────────────────┐ │ ┌────────────────────┐ │ ┌────────────┐ │
|
||||||
|
│ │ Account Health │ │ │ Tab Bar: │ │ │ Latest │ │
|
||||||
|
│ │ Scorecard │ │ │ Overview | List1 │ │ │ Interactions │
|
||||||
|
│ │ ◆ 4 KPIs │ │ │ List2 | Oppty │ │ │ │ │
|
||||||
|
│ │ (visual) │ │ │ │ │ │ ┌────────┐ │ │
|
||||||
|
│ │ │ │ │ ┌──────────────┐ │ │ │ Sarah │ │ │
|
||||||
|
│ ├─────────────────┤ │ │ │ Item 1 Card │ │ │ │ Chen │ │ │
|
||||||
|
│ │ Key Dates │ │ │ │ [Summary] │ │ │ │ Call │ │ │
|
||||||
|
│ │ Timeline │ │ │ │ [10K ft] │ │ │ │ 2d ago │ │ │
|
||||||
|
│ │ • Refresh: 6mo │ │ │ │ [Status] │ │ │ │ ⭐⭐⭐ │ │ │
|
||||||
|
│ │ • Budget: 3mo │ │ │ └──────────────┘ │ │ │ (Drill) │ │ │
|
||||||
|
│ │ • Contract: 8mo │ │ │ │ │ │└────────┘ │ │
|
||||||
|
│ │ │ │ │ ┌──────────────┐ │ │ │ │ │
|
||||||
|
│ ├─────────────────┤ │ │ │ Item 2 Card │ │ │ ├──────────┤ │
|
||||||
|
│ │ Actions │ │ │ │ [Summary] │ │ │ │ [Log new]│ │
|
||||||
|
│ │ [QBR Prep] │ │ │ │ [10K ft] │ │ │ │ │ │
|
||||||
|
│ │ [Edit Account] │ │ │ │ [Status] │ │ │ │ Related │ │
|
||||||
|
│ │ [Open Sheets] │ │ │ └──────────────┘ │ │ │ Notes │ │
|
||||||
|
│ │ [View Notes] │ │ │ │ │ │ (from MD) │ │
|
||||||
|
│ │ [Share] │ │ │ .... (3 more) │ │ │ │ │
|
||||||
|
│ │ │ │ │ │ │ │ [View all]│ │
|
||||||
|
│ └─────────────────┘ │ └────────────────────┘ │ └────────────┘ │
|
||||||
|
│ │ │ │
|
||||||
|
└──────────────────────────────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
### 4.2 Left Pane: Account Overview (10,000 ft)
|
||||||
|
|
||||||
|
**Purpose:** At a glance, is this account healthy? What's the most critical thing to know?
|
||||||
|
|
||||||
|
**Components:**
|
||||||
|
|
||||||
|
#### Health Scorecard (4 KPIs)
|
||||||
|
Visual status cards, each with:
|
||||||
|
- **Metric name** + current value
|
||||||
|
- **Trend indicator** (↑ up, ↓ down, → flat)
|
||||||
|
- **Status badge** (green / yellow / red)
|
||||||
|
- **Drillable** — click to zoom into that metric
|
||||||
|
|
||||||
|
**KPIs (MVP):**
|
||||||
|
1. **Pure Coverage** — % of total storage on Pure
|
||||||
|
- Value: 30% | Trend: ↑ +5% YoY | Status: 🟡 Opportunity
|
||||||
|
- Rationale: Shows expansion potential; top sales driver
|
||||||
|
|
||||||
|
2. **Fleet Age** — Average age of Pure systems
|
||||||
|
- Value: 4.2 yr | Trend: → flat | Status: 🟡 Refresh Window Approaching
|
||||||
|
- Rationale: Indicates refresh opportunity timing
|
||||||
|
|
||||||
|
3. **Expansion Opportunity Size** — $ value of consolidation potential
|
||||||
|
- Value: $3.5M | Trend: ↑ Growing | Status: 🟢 Pipeline-Ready
|
||||||
|
- Rationale: Deal size at a glance; guides priority
|
||||||
|
|
||||||
|
4. **Engagement Momentum** — Recency of last interaction + champion sentiment
|
||||||
|
- Value: 5 days | Trend: ↑ Active | Status: 🟢 Engaged
|
||||||
|
- Rationale: Is this account warm or cold?
|
||||||
|
|
||||||
|
#### Key Dates Timeline
|
||||||
|
Visual timeline of critical dates:
|
||||||
|
- **Refresh Date**: Next Pure system refresh
|
||||||
|
- **Budget Cycle**: When capex decisions happen
|
||||||
|
- **Contract Renewal**: When Pure contract is up
|
||||||
|
- **Next Review**: When you should reconnect
|
||||||
|
|
||||||
|
Format: Horizontal timeline or vertical list with "X days until" callouts.
|
||||||
|
|
||||||
|
#### Action Buttons (Quick nav)
|
||||||
|
- **QBR Prep** → Opens checklist template
|
||||||
|
- **Edit Account** → Opens Sheets in new tab
|
||||||
|
- **View Notes** → Opens Obsidian vault or embedded Markdown
|
||||||
|
- **Share** → (Future) generates shareable summary link
|
||||||
|
- **Log Interaction** → Quick-add form (bottom right pane)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 4.3 Center Pane: Details & Drill-Down
|
||||||
|
|
||||||
|
**Purpose:** Zoom from 10K ft into List 1 and List 2 metrics. See details, trends, and rationale.
|
||||||
|
|
||||||
|
**Tab Structure:**
|
||||||
|
|
||||||
|
#### Tab 1: Overview (Summary of all 10 items)
|
||||||
|
Shows all 5 List 1 items + all 5 List 2 items as **cards in a grid**:
|
||||||
|
- Card layout: Title | 10K ft summary | Status badge | Click to drill
|
||||||
|
- Color-coded by item type (List 1 = blue accent, List 2 = green accent)
|
||||||
|
- Scanning-friendly; can see account at a glance
|
||||||
|
|
||||||
|
#### Tab 2: Account Profile (List 1 Deep Dive)
|
||||||
|
Five expandable cards, one per List 1 item:
|
||||||
|
|
||||||
|
**Card 1: Data Footprint & Workload Breakdown**
|
||||||
|
```
|
||||||
|
┌─ Data Footprint & Workload Breakdown ───────────────────┐
|
||||||
|
│ 10K FT VIEW: │
|
||||||
|
│ 500TB current | +18% YoY | 2yr forecast: 700TB │
|
||||||
|
│ Workloads: 40% OLTP | 35% Analytics | 25% Unstructured │
|
||||||
|
│ │
|
||||||
|
│ [CLICK TO EXPAND ▼] │
|
||||||
|
│ │
|
||||||
|
│ EXPANDED VIEW: │
|
||||||
|
│ ┌─ Breakdown Table ──────────────────────────────────┐ │
|
||||||
|
│ │ Tier │ Current │ Growth │ 2yr Forecast │ Note │
|
||||||
|
│ │ OLTP │ 200TB │ +15% │ 265TB │ TX DB │
|
||||||
|
│ │ Analytics │ 175TB │ +25% │ 275TB │ DW │
|
||||||
|
│ │ Unstructured│ 125TB │ +12% │ 160TB │ Lake │
|
||||||
|
│ └────────────────────────────────────────────────────┘ │
|
||||||
|
│ │
|
||||||
|
│ ┌─ Capacity Growth Chart ────────────────────────────┐ │
|
||||||
|
│ │ [Line chart: 3yr history + 2yr forecast] │ │
|
||||||
|
│ │ Shows growth trajectory, where Pure could capture │ │
|
||||||
|
│ └────────────────────────────────────────────────────┘ │
|
||||||
|
│ │
|
||||||
|
│ CONTEXT FROM NOTES: │
|
||||||
|
│ "Customer mentioned big analytics push for FY27..." │
|
||||||
|
│ │
|
||||||
|
│ [Related Links: 10-K | Analyst Report] │
|
||||||
|
└─────────────────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
**Card 2: Current Storage Vendors & Installed Infrastructure**
|
||||||
|
```
|
||||||
|
┌─ Current Storage Vendors ──────────────────────────────┐
|
||||||
|
│ 10K FT VIEW: │
|
||||||
|
│ NetApp 50% | Pure 30% | Dell 20% (of 1200TB total) │
|
||||||
|
│ Consolidation Opportunity: HIGH │
|
||||||
|
│ │
|
||||||
|
│ [CLICK TO EXPAND ▼] │
|
||||||
|
│ │
|
||||||
|
│ EXPANDED VIEW: │
|
||||||
|
│ ┌─ Vendor Breakdown (Pie Chart) ─────────────────────┐ │
|
||||||
|
│ │ [Visual pie showing % by vendor] │ │
|
||||||
|
│ │ NetApp = oldest systems, refresh due │ │
|
||||||
|
│ └────────────────────────────────────────────────────┘ │
|
||||||
|
│ │
|
||||||
|
│ ┌─ Incumbent Systems Detail ────────────────────────┐ │
|
||||||
|
│ │ Vendor: EMC Symmetrix DMX-4 │ │
|
||||||
|
│ │ Capacity: 200TB | Age: 6 years | Status: AGING │ │
|
||||||
|
│ │ Use Case: Core banking OLTP │ │
|
||||||
|
│ │ 💡 Displacement Target: Move to Pure FlashArray │ │
|
||||||
|
│ └────────────────────────────────────────────────────┘ │
|
||||||
|
│ │
|
||||||
|
│ COMPETITIVE CONTEXT: │
|
||||||
|
│ "This EMC system is at end-of-life; customer risk- │
|
||||||
|
│ averse but willing to consolidate if migration is │
|
||||||
|
│ proven. Reference customer opportunity." │
|
||||||
|
│ │
|
||||||
|
│ [Related: Competitive Intel | Displacement Playbook] │
|
||||||
|
└──────────────────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
**Cards 3-5:** Similar drill-down structure for Business Drivers, Architecture, Budget/Authority
|
||||||
|
|
||||||
|
#### Tab 3: Pure Deployment (List 2 Deep Dive)
|
||||||
|
Five cards showing Pure-specific metrics, one per List 2 item.
|
||||||
|
|
||||||
|
**Card 1: Current Pure Installed Base**
|
||||||
|
```
|
||||||
|
┌─ Current Pure Installed Base ──────────────────────────┐
|
||||||
|
│ 10K FT VIEW: │
|
||||||
|
│ 2 FlashArray systems (150TB) | Healthy | 4.2yr avg age │
|
||||||
|
│ Headroom: 52TB | Refresh window: 18mo │
|
||||||
|
│ │
|
||||||
|
│ [CLICK TO EXPAND ▼] │
|
||||||
|
│ │
|
||||||
|
│ EXPANDED VIEW: │
|
||||||
|
│ ┌─ Systems Inventory Table ──────────────────────────┐ │
|
||||||
|
│ │ System | Type | Capacity | Util | Headroom | Age │ │
|
||||||
|
│ │ FA-P1 | FA | 75TB | 65% | 26TB | 5.1yr │ │
|
||||||
|
│ │ FA-DR | FA | 75TB | 40% | 45TB | 3.3yr │ │
|
||||||
|
│ │ Refresh Needed │ │
|
||||||
|
│ └────────────────────────────────────────────────────┘ │
|
||||||
|
│ │
|
||||||
|
│ ┌─ Utilization & Headroom Heatmap ──────────────────┐ │
|
||||||
|
│ │ [Visual: System cards with fill % + headroom bar] │ │
|
||||||
|
│ │ FA-P1: ████████ 65% USED (26TB headroom) │ │
|
||||||
|
│ │ FA-DR: █████░░░ 40% USED (45TB headroom) │ │
|
||||||
|
│ └────────────────────────────────────────────────────┘ │
|
||||||
|
│ │
|
||||||
|
│ EXPANSION IMPLICATION: │
|
||||||
|
│ "FA-P1 will need refresh/capacity add in 18 months; │
|
||||||
|
│ FA-DR has headroom for growth without additional spend" │
|
||||||
|
│ │
|
||||||
|
│ [Related: Pure1 Dashboard | Refresh Planning Guide] │
|
||||||
|
└──────────────────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
**Cards 2-5:** Performance/Satisfaction, Coverage Gaps, Refresh Cycles, Stakeholders
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 4.4 Right Pane: Unstructured Context & Interactions
|
||||||
|
|
||||||
|
**Purpose:** Connect quantitative data (left/center) to narrative context (right). See "why" behind the numbers.
|
||||||
|
|
||||||
|
**Components:**
|
||||||
|
|
||||||
|
#### Latest Interactions (Log)
|
||||||
|
Shows most recent 3-5 interactions with sentiment:
|
||||||
|
```
|
||||||
|
┌─ Interactions ────────────────────────────────────────┐
|
||||||
|
│ ⭐⭐⭐⭐⭐ Sarah Chen (VP Storage) │
|
||||||
|
│ Call — 2026-10-02 · 5 days ago │
|
||||||
|
│ "Discussed multi-site replication, pain with NetApp" │
|
||||||
|
│ Status: Strong Advocate for Pure adoption │
|
||||||
|
│ │
|
||||||
|
│ ⭐⭐⭐ Mike Lopez (CIO) │
|
||||||
|
│ Email — 2026-09-15 · 22 days ago │
|
||||||
|
│ "Budget constraints; interested in OpEx models" │
|
||||||
|
│ Status: Neutral, cost-focused │
|
||||||
|
│ │
|
||||||
|
│ ⭐⭐ Jennifer Park (CFO) │
|
||||||
|
│ Meeting — 2026-08-20 · 47 days ago │
|
||||||
|
│ "Positive on storage consolidation, capex tight" │
|
||||||
|
│ Status: Positive but budget-constrained │
|
||||||
|
│ │
|
||||||
|
│ [+ Log New Interaction] │
|
||||||
|
└───────────────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
#### Related Notes (from Markdown)
|
||||||
|
Embedded snippet from Obsidian Markdown file:
|
||||||
|
```
|
||||||
|
┌─ Discovery Notes ──────────────────────────────────────┐
|
||||||
|
│ STRATEGY THEME: Consolidation play │
|
||||||
|
│ Customer is post-acquisition; consolidating 3 data │
|
||||||
|
│ centers into 2. Big opportunity to move from multi- │
|
||||||
|
│ vendor (EMC + NetApp) to Pure standardization. │
|
||||||
|
│ │
|
||||||
|
│ RISK: Customer risk-averse on primary storage. │
|
||||||
|
│ LEVER: Success story at reference customer + DR copy. │
|
||||||
|
│ │
|
||||||
|
│ NEXT STEP: Sarah is scheduled for Q4 arch review. │
|
||||||
|
│ Come with: Multi-site replication architecture, │
|
||||||
|
│ consolidation cost model. │
|
||||||
|
│ │
|
||||||
|
│ [View Full Notes] [Edit in Obsidian] │
|
||||||
|
└───────────────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
#### Quick Actions
|
||||||
|
- **[Log Interaction]** → Popup form to add call/email/meeting
|
||||||
|
- **[View All Notes]** → Opens Obsidian file
|
||||||
|
- **[View Sheets]** → Opens Google Sheets
|
||||||
|
- **[Share Account]** → (Future) generates link
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 4.5 Responsive Behavior & Interactivity
|
||||||
|
|
||||||
|
#### Drill-Down Interactions
|
||||||
|
- **Cards expand in place** — no modal/new page; content slides down
|
||||||
|
- **Breadcrumb trail** — e.g., "Account > List 1 > Data Footprint" so you know where you are
|
||||||
|
- **Collapse others** — When one card expands, others collapse (reduces noise)
|
||||||
|
- **Smooth transitions** — Cards animate open/closed
|
||||||
|
|
||||||
|
#### Status Badges & Visual Indicators
|
||||||
|
| Status | Color | Meaning |
|
||||||
|
|--------|-------|---------|
|
||||||
|
| 🟢 Green | Good / On Track / Advocate | Positive signal |
|
||||||
|
| 🟡 Yellow | Caution / Aging / Neutral | Attention needed |
|
||||||
|
| 🔴 Red | Risk / Critical / Urgent | Action required |
|
||||||
|
| ⚪ Gray | Unknown / TBD | Need more info |
|
||||||
|
|
||||||
|
#### Data-Driven Highlights
|
||||||
|
Conditional visual emphasis on metrics:
|
||||||
|
- **Refresh window approaching** (>4yr age) → Highlighted in yellow
|
||||||
|
- **Coverage gap opportunity** (low % Pure) → Highlighted in orange
|
||||||
|
- **Budget cycle in next 90 days** → Underlined with "upcoming" tag
|
||||||
|
- **Strong champion sentiment** → Starbursts/badge next to name
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 5. Component Breakdown & Data Mapping
|
||||||
|
|
||||||
|
### 5.1 Component Hierarchy
|
||||||
|
|
||||||
|
```
|
||||||
|
DashboardApp
|
||||||
|
├── Header
|
||||||
|
│ ├── AccountName
|
||||||
|
│ ├── StatusBadge (Prospect/Customer)
|
||||||
|
│ ├── MetadataBar (Vertical, Location, Last Updated)
|
||||||
|
│ └── HeaderActions ([Share] [Edit] [Settings])
|
||||||
|
│
|
||||||
|
├── MainLayout (3-pane)
|
||||||
|
│ │
|
||||||
|
│ ├── LeftPane (Overview)
|
||||||
|
│ │ ├── HealthScorecard
|
||||||
|
│ │ │ ├── KPICard (Pure Coverage)
|
||||||
|
│ │ │ ├── KPICard (Fleet Age)
|
||||||
|
│ │ │ ├── KPICard (Opportunity Size)
|
||||||
|
│ │ │ └── KPICard (Engagement Momentum)
|
||||||
|
│ │ ├── TimelineComponent
|
||||||
|
│ │ │ ├── TimelineEvent (Refresh Date)
|
||||||
|
│ │ │ ├── TimelineEvent (Budget Cycle)
|
||||||
|
│ │ │ ├── TimelineEvent (Contract Renewal)
|
||||||
|
│ │ │ └── TimelineEvent (Next Review)
|
||||||
|
│ │ └── ActionButtons
|
||||||
|
│ │ ├── Button (QBR Prep)
|
||||||
|
│ │ ├── Button (Edit Account)
|
||||||
|
│ │ ├── Button (View Notes)
|
||||||
|
│ │ └── Button (Share)
|
||||||
|
│ │
|
||||||
|
│ ├── CenterPane (Details & Drill-Down)
|
||||||
|
│ │ ├── TabBar
|
||||||
|
│ │ │ ├── Tab (Overview)
|
||||||
|
│ │ │ ├── Tab (List 1: Account Profile)
|
||||||
|
│ │ │ ├── Tab (List 2: Pure Deployment)
|
||||||
|
│ │ │ └── Tab (Opportunities — future)
|
||||||
|
│ │ │
|
||||||
|
│ │ └── TabContent (varies by tab)
|
||||||
|
│ │ └── DetailsCard (repeating)
|
||||||
|
│ │ ├── CardHeader (title + status)
|
||||||
|
│ │ ├── CardSummary (10K ft view)
|
||||||
|
│ │ ├── ExpandButton
|
||||||
|
│ │ └── ExpandedContent (on click)
|
||||||
|
│ │ ├── DetailTable / Chart
|
||||||
|
│ │ ├── TrendVisualization
|
||||||
|
│ │ └── RelatedContext
|
||||||
|
│ │
|
||||||
|
│ └── RightPane (Context)
|
||||||
|
│ ├── InteractionLog
|
||||||
|
│ │ └── InteractionItem (repeating)
|
||||||
|
│ │ ├── Sentiment (stars)
|
||||||
|
│ │ ├── Contact Info
|
||||||
|
│ │ ├── Timestamp
|
||||||
|
│ │ └── Summary
|
||||||
|
│ ├── RelatedNotes
|
||||||
|
│ │ └── NotesSnippet
|
||||||
|
│ └── QuickActions
|
||||||
|
│ ├── Button (Log Interaction)
|
||||||
|
│ ├── Button (View All Notes)
|
||||||
|
│ └── Button (View Sheets)
|
||||||
|
```
|
||||||
|
|
||||||
|
### 5.2 Data Source Mapping
|
||||||
|
|
||||||
|
| Component | Data Source | Sheet Location | Notes |
|
||||||
|
|-----------|---|---|---|
|
||||||
|
| **Account Name** | Account tab | Name | |
|
||||||
|
| **Status Badges** | Account tab | Status, Vertical, Location | |
|
||||||
|
| **Health Scorecard** | Account + Pure-Deployment tabs | Multiple cells + formulas | Calculated KPIs |
|
||||||
|
| **Timeline** | Account tab | Columns: Next Refresh Date, Budget Cycle, Contract End, Next Review | |
|
||||||
|
| **List 1 Cards** | Account tab | Tabs: Item 1-5 data | Five expandable items |
|
||||||
|
| **List 2 Cards** | Pure-Deployment tab | Tabs: Item 1-5 data | Five expandable items |
|
||||||
|
| **Interaction Log** | Interactions tab | Contact, Type, Date, Sentiment, Summary | Sorted by date DESC |
|
||||||
|
| **Related Notes** | Markdown file (Obsidian) | Fetched via API or embed | Text snippet + link |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 6. Visual Design Principles
|
||||||
|
|
||||||
|
### Color Palette (Themeable)
|
||||||
|
- **Accent Blue** (Primary): List 1 items, account overview
|
||||||
|
- **Accent Green** (Secondary): List 2 items, Pure deployment
|
||||||
|
- **Status Green** (Success): Healthy, positive, on-track
|
||||||
|
- **Status Yellow** (Warning): Approaching refresh, caution needed
|
||||||
|
- **Status Red** (Critical): Urgent action required
|
||||||
|
- **Neutral Gray**: Unknown, TBD, secondary content
|
||||||
|
- **Text Dark Gray** (Light mode) / **Text Light Gray** (Dark mode)
|
||||||
|
- **Background**: Light/dark mode adaptive
|
||||||
|
|
||||||
|
### Typography
|
||||||
|
- **Header**: Large, bold, account name stands out
|
||||||
|
- **Tab titles**: Medium weight, clear tab distinction
|
||||||
|
- **Card titles**: Semi-bold, clickable indicator (▼)
|
||||||
|
- **Data values**: Monospace for numbers (easier to scan)
|
||||||
|
- **Labels**: Smaller, muted color
|
||||||
|
|
||||||
|
### Spacing & Layout
|
||||||
|
- **Panes**: Equal width (33% each) or responsive flex at smaller widths
|
||||||
|
- **Cards**: Padding ~20px, margin ~16px between cards
|
||||||
|
- **Drill-down**: Animated 200ms expand/collapse
|
||||||
|
- **Mobile**: Stack panes vertically (future consideration)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 7. Navigation & User Flows
|
||||||
|
|
||||||
|
### Flow 1: Pre-Call Prep (15 min before discovery)
|
||||||
|
```
|
||||||
|
User lands on dashboard
|
||||||
|
↓
|
||||||
|
Glances at Health Scorecard (30 sec) — "Pure coverage 30%, fleet aging, $3.5M upside"
|
||||||
|
↓
|
||||||
|
Checks Key Dates Timeline (30 sec) — "Budget cycle in 3 mo, refresh in 18 mo"
|
||||||
|
↓
|
||||||
|
Clicks "QBR Prep" action → Opens checklist template in new tab
|
||||||
|
↓
|
||||||
|
Scrolls to Center pane, clicks "Current Vendors" card to see EMC footprint
|
||||||
|
↓
|
||||||
|
Reads right pane: "Customer risk-averse on primary storage; use reference story"
|
||||||
|
↓
|
||||||
|
Click [Log Interaction] → Pre-fills with today's call, ready to document post-call
|
||||||
|
```
|
||||||
|
|
||||||
|
### Flow 2: Competitive Displacement Hunt
|
||||||
|
```
|
||||||
|
User is looking for displacement opportunities
|
||||||
|
↓
|
||||||
|
Opens Account dashboard
|
||||||
|
↓
|
||||||
|
Glances at Scorecard: "Pure coverage 30%" → Opportunity
|
||||||
|
↓
|
||||||
|
Clicks "Data Footprint" card → Sees workload breakdown
|
||||||
|
↓
|
||||||
|
Clicks "Current Vendors" card → Sees EMC system (200TB, 6yr old, primary OLTP)
|
||||||
|
↓
|
||||||
|
Clicks "Coverage Gaps" card → Confirms: "EMC Symmetrix not on Pure yet"
|
||||||
|
↓
|
||||||
|
Reads notes: "Customer risk-averse but willing to migrate if proven"
|
||||||
|
↓
|
||||||
|
Action: Find reference customer, prepare migration playbook for next call
|
||||||
|
```
|
||||||
|
|
||||||
|
### Flow 3: Expansion Planning
|
||||||
|
```
|
||||||
|
User reviewing account for renewal/expansion
|
||||||
|
↓
|
||||||
|
Glances at Scorecard: Fleet age, Opportunity size, Engagement momentum
|
||||||
|
↓
|
||||||
|
Clicks "Fleet Age" card → Sees FA-P1 refresh window in 18 months
|
||||||
|
↓
|
||||||
|
Clicks "Refresh Cycles" card → Confirms capex cycle and window
|
||||||
|
↓
|
||||||
|
Checks Stakeholder info in right pane → "Sarah (VP Storage) is champion, strong advocate"
|
||||||
|
↓
|
||||||
|
Clicks "Opportunities" tab (future) → See pipeline: Analytics consolidation (Q2 2027, $1.5M)
|
||||||
|
↓
|
||||||
|
Action: Schedule architecture review with Sarah for Q1; prepare proposal for analytics move
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 8. Data Sync & Freshness
|
||||||
|
|
||||||
|
### MVP Approach: Manual Sync
|
||||||
|
- **Sheet → Dashboard**: Copy-paste JSON export or Google Sheets API call (daily/on-demand)
|
||||||
|
- **Markdown → Dashboard**: Fetch from Obsidian API or GitHub if synced
|
||||||
|
- **Freshness**: Dashboard is "point-in-time snapshot" at time of load
|
||||||
|
- **Update frequency**: User refreshes page or manually syncs from edit screens
|
||||||
|
|
||||||
|
### Future: Live Sync
|
||||||
|
- Dashboard queries Google Sheets API in real-time
|
||||||
|
- Interactions logged directly to Sheets (no manual re-entry)
|
||||||
|
- Markdown fetched from Obsidian Sync API
|
||||||
|
- Auto-refresh KPIs every 5 minutes
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 9. Extensibility Points (Future Phases)
|
||||||
|
|
||||||
|
### Phase 2: Relationships & Interaction History
|
||||||
|
- **Tab 4: Relationships** — Org chart, sentiment timeline, interaction history
|
||||||
|
- **Interaction log** — Searchable, filterable by contact, type, sentiment
|
||||||
|
- **Sentiment analysis** — Chart showing mood trend over time
|
||||||
|
|
||||||
|
### Phase 3: Opportunities & Pipeline
|
||||||
|
- **Tab 5: Opportunities** — Consolidation roadmap, deal timeline, revenue forecast
|
||||||
|
- **Milestone tracking** — Countdown to RFP, contract close, etc.
|
||||||
|
|
||||||
|
### Phase 4: Financial Modeling
|
||||||
|
- **10-K integration** — Embed PDF link, key metrics extracted
|
||||||
|
- **Opportunity forecasting** — If analytics consolidates, revenue impact
|
||||||
|
- **Budget impact model** — Capex vs. OpEx trade-off calculator
|
||||||
|
|
||||||
|
### Phase 5: Industry & Competitive Context
|
||||||
|
- **Industry trends** — Curated insights relevant to account
|
||||||
|
- **Competitor tracking** — Win/loss intelligence, displacement playbooks
|
||||||
|
- **Market context** — Industry growth rates, regulatory changes
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 10. Technical Architecture
|
||||||
|
|
||||||
|
### Technology Stack
|
||||||
|
- **Frontend**: React (or vanilla JS if keeping simple)
|
||||||
|
- **Styling**: Tailwind CSS (or custom CSS-in-JS)
|
||||||
|
- **Data sources**:
|
||||||
|
- Google Sheets API (for Account, Pure-Deployment, Relationships, Financials tabs)
|
||||||
|
- Markdown file (from Obsidian or GitHub)
|
||||||
|
- **Deployment**: Claude artifact (publishable, shareable URL) or self-hosted on homelab
|
||||||
|
- **Build**: Vite (fast dev) or Create React App
|
||||||
|
|
||||||
|
### API Integration (MVP)
|
||||||
|
```
|
||||||
|
Frontend (React)
|
||||||
|
↓
|
||||||
|
├─→ Google Sheets API v4
|
||||||
|
│ └─ Fetch: Account!A:Z, PureDeployment!A:Z, Relationships!A:Z, etc.
|
||||||
|
│ Rate: On-demand or 5-min cache
|
||||||
|
│
|
||||||
|
└─→ Markdown fetch (via Obsidian API or raw GitHub/Drive link)
|
||||||
|
└─ Fetch: Markdown content, parse for snippets
|
||||||
|
```
|
||||||
|
|
||||||
|
### State Management
|
||||||
|
- **Client-side state**: React hooks (useState, useEffect)
|
||||||
|
- **Server state**: Google Sheets is source of truth
|
||||||
|
- **UI state**: Which tab active, which card expanded
|
||||||
|
- **No local storage** (MVP): Always fresh from source
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 11. Accessibility & Usability
|
||||||
|
|
||||||
|
### Keyboard Navigation
|
||||||
|
- Tab through cards, tabs, buttons
|
||||||
|
- Enter/Space to expand cards
|
||||||
|
- Escape to collapse all
|
||||||
|
- Ctrl/Cmd+Click to open links in new tab
|
||||||
|
|
||||||
|
### Screen Readers
|
||||||
|
- Semantic HTML (headers, nav, main, article)
|
||||||
|
- ARIA labels on custom components
|
||||||
|
- Heading hierarchy (H1 = account name, H2 = tabs, H3 = card titles)
|
||||||
|
|
||||||
|
### Color Contrast
|
||||||
|
- All text meets WCAG AA standards
|
||||||
|
- Status indicators have labels (not color alone)
|
||||||
|
- Links underlined or clearly differentiated
|
||||||
|
|
||||||
|
### Mobile Responsiveness (Future)
|
||||||
|
- Stack panes vertically on small screens
|
||||||
|
- Touch-friendly button sizes (44px minimum)
|
||||||
|
- Collapsible sections for readability
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 12. Success Metrics (MVP)
|
||||||
|
|
||||||
|
| Metric | Target | How to Measure |
|
||||||
|
|--------|--------|---|
|
||||||
|
| **Time to account snapshot** | <2 min to full context | User time log |
|
||||||
|
| **Drill-down effectiveness** | Find key metric in <30 sec | User task test |
|
||||||
|
| **Information completeness** | All 10 items readily visible | Checklist |
|
||||||
|
| **Visual clarity** | No confusion on next steps | User feedback |
|
||||||
|
| **Engagement** | Used for all 3 use cases equally | Usage logs |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 13. Known Constraints & Trade-offs
|
||||||
|
|
||||||
|
| Constraint | Impact | Mitigation |
|
||||||
|
|-----------|--------|---|
|
||||||
|
| **Manual sync (MVP)** | Data can lag if Sheets updated but dashboard not refreshed | Clear "last updated" timestamp; button to manual sync |
|
||||||
|
| **No real-time collaboration** | If account team edits Sheets while viewing dashboard, changes won't appear until reload | Future: implement live sync |
|
||||||
|
| **Single-customer dashboard** | Can't compare metrics across accounts in MVP | Future: roll-up view with filtering |
|
||||||
|
| **API rate limits (Sheets)** | Can't refresh dashboard every second | Cache on client; user triggers refresh manually |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 14. Success Criteria for Prototype
|
||||||
|
|
||||||
|
✅ **Must Have (MVP)**
|
||||||
|
- [ ] All 10 items (List 1 + List 2) visible and organized
|
||||||
|
- [ ] 3-pane layout functioning (left/center/right)
|
||||||
|
- [ ] Cards expand/collapse on click with animation
|
||||||
|
- [ ] Health scorecard with 4 KPIs calculated
|
||||||
|
- [ ] Timeline showing key dates
|
||||||
|
- [ ] Sample data flowing in from mock Sheets
|
||||||
|
- [ ] Navigation between tabs (Overview, List 1, List 2)
|
||||||
|
- [ ] Status badges and visual indicators rendering correctly
|
||||||
|
|
||||||
|
⚡ **Should Have (Nice to Have)**
|
||||||
|
- [ ] Trend indicators (↑ ↓ →) on KPI cards
|
||||||
|
- [ ] Sample charts (pie, line) in expanded views
|
||||||
|
- [ ] Markdown snippet embedded in right pane
|
||||||
|
- [ ] Interaction log with sentiment stars
|
||||||
|
- [ ] Dark mode toggle
|
||||||
|
|
||||||
|
🎯 **Nice to Have (Future)**
|
||||||
|
- [ ] Google Sheets API actually connected (MVP uses mock data)
|
||||||
|
- [ ] Relationships tab structure visible
|
||||||
|
- [ ] QBR Prep modal/checklist
|
||||||
|
- [ ] Share functionality
|
||||||
|
- [ ] Export to PDF
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 15. Design Review Checklist
|
||||||
|
|
||||||
|
**Questions for Ryan before prototype:**
|
||||||
|
|
||||||
|
1. ✅ Is the 3-pane layout clear? Does it support the 10K → ground zoom?
|
||||||
|
2. ✅ Are the 4 KPIs the right ones, or would you change them?
|
||||||
|
3. ✅ Does the drill-down interaction (click card → expand) feel right, or prefer modal?
|
||||||
|
4. ✅ Should the right pane be scrollable independently, or scroll with center pane?
|
||||||
|
5. ✅ Any major UX concerns with the navigation flow?
|
||||||
|
6. ✅ Is the timeline component clear (horizontal bar vs. vertical list)?
|
||||||
|
7. ✅ Color palette acceptable, or want different accent colors?
|
||||||
|
8. ✅ Any tabs or components you'd add/remove for MVP?
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Document Status:** Ready for Design Review & Feedback
|
||||||
|
**Next Step:** Prototype build (pending approval of this design)
|
||||||
@@ -0,0 +1,257 @@
|
|||||||
|
# Top-5 Account Intelligence Lists for Enterprise Storage SE
|
||||||
|
|
||||||
|
**For:** Pre-Sales Systems Engineers at Pure Storage
|
||||||
|
**Focus Verticals:** Financial Services, Retail/Manufacturing
|
||||||
|
**Target Accounts:** Fortune 1000 / Global 2000
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## LIST 1: ANY CUSTOMER OR PROSPECT
|
||||||
|
### First Discovery Call + Competitive Displacement + Expansion Foundation
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 1. **Data Footprint and Workload Breakdown**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Total addressable storage capacity (current + 2-year projection)
|
||||||
|
- Workload tier split: critical OLTP (databases, transactional), warm operational analytics (data warehouses, ML training sets), unstructured (data lakes, backups, archives)
|
||||||
|
- Annual growth rate
|
||||||
|
- Typical IO patterns (sequential vs. random, read/write mix)
|
||||||
|
- Workload sources: core business apps, digital channels, analytics platforms, third-party integrations
|
||||||
|
|
||||||
|
**Why it ranks #1:**
|
||||||
|
This is your credibility foundation for the discovery call. Large enterprises in financial services and retail/manufacturing operate at scale—you need to know if they're managing 10PB or 500PB of storage before you can ask intelligent questions about consolidation, resilience, or performance. For competitive displacement, it tells you the total addressable market and which workloads are most valuable to move. For expansion, it shows you where growth is (analytics workloads often outpace transactional growth in these verticals).
|
||||||
|
|
||||||
|
**Vertical differences:**
|
||||||
|
- **Financial services:** Regulatory data tiers (Basel III, Dodd-Frank, GDPR-driven data governance), transaction volumes, archive-to-compliance mandates, and fraud detection datasets are outsized here.
|
||||||
|
- **Retail/manufacturing:** Omnichannel transaction data, supply chain event data, and IoT/sensor streams create different growth patterns—often unstructured-heavy.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
Account team, analyst kickoff, customer IT strategy documents. If public: earnings calls (capex guidance), analyst reports on data center expansion. **Hard to verify fully from public sources—lean on the account team and discovery conversation.** Pure1 for existing customers (capacity trends, growth rates).
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 2. **Current Storage Vendor(s) and Installed Infrastructure**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Primary vendor(s), total installed capacity per vendor, system age/generation
|
||||||
|
- Deployment model (on-prem, cloud-hosted)
|
||||||
|
- Vendor concentration (single-vendor, multi-vendor)
|
||||||
|
- Capacity consolidation potential (old systems due refresh, overlapping vendors)
|
||||||
|
- Competitive systems they've ruled out or are evaluating
|
||||||
|
|
||||||
|
**Why it ranks #2:**
|
||||||
|
This is the competitive map. In discovery, you need to know who you're up against to ask credible questions about their stack. For displacement, this is your roadmap—old NetApp or EMC systems are your opening; vendor sprawl is your consolidation story. For expansion, it shows where Pure is (or isn't) and where you can grow.
|
||||||
|
|
||||||
|
**Applies to both verticals:**
|
||||||
|
Regulatory and operational requirements often enforce heterogeneous stacks (legacy core systems, newer analytics platforms), creating multi-vendor complexity and Pure's consolidation angle.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
Account team, customer IT contacts, Gartner/IDC reports, job postings (hiring for specific platforms signals infrastructure). Pure's competitive intel teams (if available in your region). **Harder to get from public sources—interview in discovery.**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 3. **Business Drivers and Strategic Imperatives**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- What's moving their infrastructure strategy in the next 12–24 months?
|
||||||
|
- Digital transformation (cloud-first, API-led architecture)
|
||||||
|
- M&A (data center consolidation, platform rationalization)
|
||||||
|
- Regulatory change (data residency, compliance modernization)
|
||||||
|
- Cost reduction (capex or opex pressure)
|
||||||
|
- Performance demands (real-time analytics, AI/ML acceleration)
|
||||||
|
- Geographic expansion (multi-site, disaster recovery)
|
||||||
|
|
||||||
|
**Why it ranks #3:**
|
||||||
|
This explains *why* they'll spend and *when*. For discovery, it tells you what your conversation should be anchored to—cost pressure is a different conversation than compliance urgency. For displacement, it reveals openings (legacy vendor can't support cloud migration; incumbent doesn't scale for analytics). For expansion, it shows where budget flows and growth cycles.
|
||||||
|
|
||||||
|
**Vertical differences:**
|
||||||
|
- **Financial services:** Regulatory change (Fed data residency mandates, CCAR/stress test infrastructure), fraud detection (AI/ML workloads), and open banking/fintech competition drive transformation.
|
||||||
|
- **Retail/manufacturing:** Omnichannel unification, supply chain visibility, and sustainability reporting (ESG data) are primary drivers; cost pressure is often secondary.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
Earnings calls (CFO and CRO commentary), industry analyst reports, customer executives in discovery (CEOs and CFOs speak to this), account team (relationship intelligence). Regulatory announcements for financial services. **Public sources vary—direct ask is usually most productive.**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 4. **Infrastructure Architecture and Resilience Model**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Topology: single data center, active-active multi-site, hub-and-spoke?
|
||||||
|
- Failover strategy (RPO/RTO targets, synchronous vs. asynchronous replication)
|
||||||
|
- Cloud presence (public cloud, hybrid, private cloud)
|
||||||
|
- Containerization and Kubernetes adoption
|
||||||
|
- Storage tiers and tiering automation
|
||||||
|
- Backup/archive strategy (separate systems, integrated)
|
||||||
|
|
||||||
|
**Why it ranks #4:**
|
||||||
|
This determines *which* Pure solutions fit and how. Knowing they're multi-site tells you Evergreen model and replication are critical; knowing they have Kubernetes tells you Portworx is on the menu; knowing they're chasing sub-second RTO tells you FlashArray's performance story matters. For discovery, it frames the conversation around resilience or performance. For displacement, it shows where Pure's architecture outperforms incumbent (e.g., Evergreen's native replication vs. bolted-on replication). For expansion, it guides where to add capacity.
|
||||||
|
|
||||||
|
**Vertical differences:**
|
||||||
|
- **Financial services:** Recovery requirements are often strict (RTO <1hr, RPO <15min); multi-site is standard; compliance mandates geographic separation.
|
||||||
|
- **Retail/manufacturing:** Multi-site is common (stores, plants, distribution); RTO is important but often longer than financial services; hybrid cloud adoption is accelerating.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
Account team, technical RFI/RFQ documents, infrastructure diagrams (security-sensitive—may not be public). Discovery conversation with IT infrastructure/storage teams. **Hard from public sources.**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 5. **Budget Cycle, Capital Allocation, and Buying Authority**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Capex budget cycle and approval gates (who approves? quarterly, annual, rolling?)
|
||||||
|
- Capex vs. opex preference (traditional capex, Evergreen-style subscription, OpEx-only mandate)
|
||||||
|
- Budget envelope for infrastructure over next 2 years
|
||||||
|
- Preferred buying patterns (competitive bid, existing vendor preference, tech refresh cycle)
|
||||||
|
- Influencers and decision-makers (CIO, VP Storage, business unit leaders, CFO)
|
||||||
|
|
||||||
|
**Why it ranks #5:**
|
||||||
|
This is the "when and how to sell" lever. It's less about discovery credibility (though knowing budget is essential) and more about deal realism. For discovery, it tells you timing and buying authority to route follow-ups. For displacement, it tells you if capex is available or if you need to frame Evergreen as an alternative. For expansion, it reveals budget headroom and buying rhythm.
|
||||||
|
|
||||||
|
**Applies to both verticals:**
|
||||||
|
Financial services often have tighter capex scrutiny and longer approval cycles; retail/manufacturing may have faster refresh cycles but more budget constraints post-acquisition integration.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
Account team relationship notes, past deal history, 10-K/10-Q filings (capex guidance), analyst reports, budget forecasts shared in customer relationships. **Rarely fully public—account team and direct relationship intelligence are key.**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## LIST 2: EXISTING CUSTOMERS — PURE STORAGE DEPLOYMENT SPECIFICS
|
||||||
|
### Expansion + Retention + Competitive Defense
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 1. **Current Pure Installed Base, Deployment Pattern, and Capacity**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- FlashArray systems (models, capacity per system, tier across data centers or cloud regions)
|
||||||
|
- FlashBlade deployments (scale-out analytics use cases, capacity)
|
||||||
|
- Portworx deployments (if any; containerized workloads, environments)
|
||||||
|
- Age of systems (when deployed; refresh cycle status)
|
||||||
|
- Geographic footprint (on-prem across which data centers, any cloud-hosted Pure?)
|
||||||
|
- Utilization and headroom (at capacity, growing into headroom, or sparse?)
|
||||||
|
|
||||||
|
**Why it ranks #1:**
|
||||||
|
You can't expand without knowing your baseline. For expansion, this is your starting point—you need to know what they own to identify the next sale (add capacity, new tier, new workload). For retention, it's your health baseline (old systems more likely to churn). For competitive defense, it shows Pure's footprint and where competitors might try to take share.
|
||||||
|
|
||||||
|
**Key indicators for retention/expansion:**
|
||||||
|
Systems older than 5 years are refresh candidates; sparse utilization may indicate underutilized tier or expansion opportunity; multi-site Pure deployments are higher-value accounts.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
**Pure1 (your best data source—capacity, performance, age, location),** internal Pure account data, customer IT/storage teams. Direct ask in customer reviews and strategic business reviews (QBR/SBR).
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 2. **Performance, Utilization, and Customer Satisfaction**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Pure1 performance metrics (latency, IOPS achieved vs. provisioned, dedupe/compression ratios, capacity growth rate)
|
||||||
|
- Storage team feedback (support experience, feature requests, known pain points)
|
||||||
|
- Performance satisfaction (are performance SLAs being met?)
|
||||||
|
- Operational efficiency gains (cost per GB, power/cooling reduction)
|
||||||
|
- Customer sentiment (NPS or equivalent; any churn signals?)
|
||||||
|
|
||||||
|
**Why it ranks #2:**
|
||||||
|
This tells you expansion potential vs. churn risk. If they're unsatisfied, expansion is at risk (competitor threat, bargaining power). If they're thriving on Pure, expansion is easier (proven business case). For retention, this is your early warning system. For expansion, high satisfaction is your foundation for upsells (new workload, new tier, cloud-native).
|
||||||
|
|
||||||
|
**Vertical differences:**
|
||||||
|
- **Financial services:** Customers often have strict uptime/performance mandates.
|
||||||
|
- **Retail/manufacturing:** Often cost-conscious and may trade performance for efficiency.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
**Pure1 (performance analytics),** NPS/CSAT surveys, QBR discussions, support ticket sentiment, sales/SE relationship notes. Direct ask: "How is Pure performing for you?"
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 3. **Data Footprint Not Yet on Pure / Coverage Gap Analysis**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Percentage of their total storage on Pure vs. other vendors
|
||||||
|
- Workload segments not on Pure (e.g., older OLTP databases on EMC, analytics on Hadoop/object storage, backups on separate vendor)
|
||||||
|
- Highest-value data not on Pure (revenue-generating apps, critical analytics)
|
||||||
|
- Consolidation opportunities (multi-vendor overlap, legacy systems ready to refresh)
|
||||||
|
- Workloads Pure could address but hasn't yet (emerging use cases, cloud data, new business initiatives)
|
||||||
|
|
||||||
|
**Why it ranks #3:**
|
||||||
|
This is your expansion TAM within the account. For expansion, it shows where growth comes from (consolidation opportunity, new workload, tier migration). For competitive defense, it identifies where competitors will attack (the gap is their opening). For retention, it's leverage—you want to own more of their data.
|
||||||
|
|
||||||
|
**Vertical differences:**
|
||||||
|
- **Financial services:** Critical OLTP often stays on incumbent (lower risk perception); newer analytics and fraud detection data are Pure opportunities.
|
||||||
|
- **Retail/manufacturing:** Supply chain/IoT data and unstructured analytics are often on non-Pure platforms; consolidation gains are high here.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
**Pure1 (shows only Pure capacity—you need to ask for total footprint),** customer IT (data inventory), discovery/expansion conversations. **Often not transparent from public sources—direct conversation essential.**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 4. **Upcoming Infrastructure Initiatives and Technology Refresh Cycles**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Planned data center consolidation or modernization
|
||||||
|
- System refresh dates (when is their oldest Pure system past end-of-support? When's the next capex cycle?)
|
||||||
|
- Cloud migration plans (moving workloads to cloud; implications for on-prem storage)
|
||||||
|
- New workloads (AI/ML platforms, real-time analytics, new business lines)
|
||||||
|
- Multi-site expansion or disaster recovery modernization
|
||||||
|
|
||||||
|
**Why it ranks #4:**
|
||||||
|
Timing is everything in expansion. Refresh cycles are your biggest lever (old systems = new capex = new opportunity). Cloud migration can cut Pure TAM or open Portworx opportunities. New workloads are expansion hooks. For expansion, this is your calendar. For retention, knowing refresh timing lets you plan defense early.
|
||||||
|
|
||||||
|
**Applies to both verticals:**
|
||||||
|
Financial services often have annual capex cycles tied to business planning; retail/manufacturing may refresh faster or slower depending on store/plant footprint changes.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
Customer IT roadmap (often multi-year), Pure account team, QBR discussions, earnings announcements (for large public customers, CapEx guidance), customer executives. Sometimes in customer's published IT strategy.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 5. **Stakeholder Relationships, Expansion Readiness, and Competitive Threats**
|
||||||
|
|
||||||
|
**What to capture:**
|
||||||
|
- Key stakeholders (CIO, VP Storage, business unit leaders, security/compliance officers)
|
||||||
|
- Champion(s) (who advocates for Pure?)
|
||||||
|
- Relationship temperature (trust, satisfaction, barriers)
|
||||||
|
- Competitive interest (have they mentioned other vendors? RFPs? Evaluation?)
|
||||||
|
- Budget headroom (will they invest more in storage in next 12–24 months?)
|
||||||
|
- Expansion appetite (are they open to moving more workloads to Pure, or focused on optimization?)
|
||||||
|
|
||||||
|
**Why it ranks #5:**
|
||||||
|
This is your "how to expand" lever. Knowing who the champion is tells you how to navigate. Knowing if they're under competitive attack tells you how urgent your defense is. Knowing budget appetite tells you if expansion is realistic. For expansion, this is your relationship risk/opportunity assessment. For retention, it's your early warning for churn or your pathway for growth.
|
||||||
|
|
||||||
|
**Applies to both verticals:**
|
||||||
|
In large enterprises, storage decisions often flow through business unit leaders (not just IT); understanding where Pure fits in their strategic priorities is key.
|
||||||
|
|
||||||
|
**Where to get it:**
|
||||||
|
Account team relationship notes, past deal history, QBR feedback, sales/SE interactions, industry/analyst events. Direct ask in customer conversations: "Where do you see us helping you grow?"
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Summary: Why This Order Matters
|
||||||
|
|
||||||
|
**List 1** (any customer/prospect) moves from **foundational understanding** (what and who) → **context** (why and how) → **execution** (when and who decides). This sequence builds credibility in discovery while revealing competitive and expansion levers.
|
||||||
|
|
||||||
|
**List 2** (existing customer Pure deployments) moves from **your current position** (what you have) → **relationship health** (how it's performing) → **opportunity size** (what you could have) → **timing** (when they'll buy) → **execution** (how to navigate the sale). This sequence is your expansion playbook.
|
||||||
|
|
||||||
|
### Key Callout
|
||||||
|
In both lists, **items 1–3 should drive 80% of your discovery and account strategy effort**. Items 4–5 refine timing and approach. **Start here, then layer in the operational details** (support SLAs, feature adoption, roadmap alignment) as you deepen the relationship.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Quick Reference: Source Hierarchy by Item
|
||||||
|
|
||||||
|
| Item | Primary Source | Secondary Source | Public Availability |
|
||||||
|
|------|---|---|---|
|
||||||
|
| **List 1 #1** – Data Footprint | Account team, customer IT | Earnings calls, analyst reports | Moderate (public guidance varies) |
|
||||||
|
| **List 1 #2** – Current Vendors | Account team, IT contacts | Job postings, Gartner reports | Low (often internal knowledge) |
|
||||||
|
| **List 1 #3** – Business Drivers | Customer executives, analyst reports | Earnings calls, regulatory filings | Moderate (CEOs/CFOs speak to this) |
|
||||||
|
| **List 1 #4** – Architecture | Technical RFI/RFQ, account team | Discovery conversation | Low (security-sensitive) |
|
||||||
|
| **List 1 #5** – Budget/Authority | Account team, past deal history | 10-K/10-Q, customer relationships | Low (relationship intelligence) |
|
||||||
|
| **List 2 #1** – Pure Installed Base | **Pure1** (best source), account data | Customer IT, QBR | Account-internal only |
|
||||||
|
| **List 2 #2** – Performance/Satisfaction | **Pure1**, NPS surveys | Support tickets, QBR discussions | Account-internal only |
|
||||||
|
| **List 2 #3** – Coverage Gaps | Customer IT inventory, discovery | Account team insights | Low (direct conversation required) |
|
||||||
|
| **List 2 #4** – Refresh Cycles | Customer IT roadmap, account team | QBR, earnings announcements | Low-Moderate (customer-dependent) |
|
||||||
|
| **List 2 #5** – Stakeholder/Competitive | Account team, sales history | QBR feedback, customer conversations | Account-internal only |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Use this as your go-to reference before discovery calls, account strategy reviews, and expansion planning.**
|
||||||
+3
-3
@@ -54,7 +54,7 @@
|
|||||||
|
|
||||||
# (pathspec) Colon-separated paths in which Ansible will search for collections content. Collections must be in nested *subdirectories*, not directly in these directories. For example, if ``COLLECTIONS_PATHS`` includes ``'{{ ANSIBLE_HOME ~ "/collections" }}'``, and you want to add ``my.collection`` to that directory, it must be saved as ``'{{ ANSIBLE_HOME} ~ "/collections/ansible_collections/my/collection" }}'``.
|
# (pathspec) Colon-separated paths in which Ansible will search for collections content. Collections must be in nested *subdirectories*, not directly in these directories. For example, if ``COLLECTIONS_PATHS`` includes ``'{{ ANSIBLE_HOME ~ "/collections" }}'``, and you want to add ``my.collection`` to that directory, it must be saved as ``'{{ ANSIBLE_HOME} ~ "/collections/ansible_collections/my/collection" }}'``.
|
||||||
|
|
||||||
;collections_path=/Users/rblundon/.ansible/collections:/usr/share/ansible/collections
|
collections_path=/opt/ansible-collections:/usr/share/ansible/collections
|
||||||
|
|
||||||
# (boolean) A boolean to enable or disable scanning the sys.path for installed collections.
|
# (boolean) A boolean to enable or disable scanning the sys.path for installed collections.
|
||||||
;collections_scan_sys_path=True
|
;collections_scan_sys_path=True
|
||||||
@@ -209,7 +209,7 @@ private_key_file=~/.ssh/ansible
|
|||||||
remote_user=wed
|
remote_user=wed
|
||||||
|
|
||||||
# (pathspec) Colon-separated paths in which Ansible will search for Roles.
|
# (pathspec) Colon-separated paths in which Ansible will search for Roles.
|
||||||
roles_path=/opt/git/homelab/ansible/playbooks/roles:/Users/rblundon/.ansible/roles:/usr/share/ansible/roles:/etc/ansible/roles
|
roles_path=./roles
|
||||||
|
|
||||||
# (string) Set the main callback used to display Ansible output. You can only have one at a time.
|
# (string) Set the main callback used to display Ansible output. You can only have one at a time.
|
||||||
# You can have many other callbacks, but just one can be in charge of stdout.
|
# You can have many other callbacks, but just one can be in charge of stdout.
|
||||||
@@ -262,7 +262,7 @@ roles_path=/opt/git/homelab/ansible/playbooks/roles:/Users/rblundon/.ansible/rol
|
|||||||
|
|
||||||
# (path) The vault password file to use. Equivalent to ``--vault-password-file`` or ``--vault-id``.
|
# (path) The vault password file to use. Equivalent to ``--vault-password-file`` or ``--vault-id``.
|
||||||
# If executable, it will be run and the resulting stdout will be used as the password.
|
# If executable, it will be run and the resulting stdout will be used as the password.
|
||||||
;vault_password_file=
|
vault_password_file=/home/hermes/.vault_pass.txt
|
||||||
|
|
||||||
# (integer) Sets the default verbosity, equivalent to the number of ``-v`` passed in the command line.
|
# (integer) Sets the default verbosity, equivalent to the number of ``-v`` passed in the command line.
|
||||||
;verbosity=0
|
;verbosity=0
|
||||||
|
|||||||
@@ -0,0 +1,6 @@
|
|||||||
|
---
|
||||||
|
- name: Create jarvis user and deploy SSH key
|
||||||
|
hosts: all
|
||||||
|
become: true
|
||||||
|
roles:
|
||||||
|
- jarvis_user
|
||||||
@@ -0,0 +1,193 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# Semaphore configuration-as-code
|
||||||
|
# ============================================================================
|
||||||
|
# Drives a freshly-deployed Semaphore instance into its desired state via
|
||||||
|
# the Semaphore REST API. Idempotent: every object is checked first; only
|
||||||
|
# missing ones are created. Existing objects are left alone.
|
||||||
|
#
|
||||||
|
# Loaded from group_vars/all/semaphore.yml so that the configuration is
|
||||||
|
# version-controlled in the homelab repo and survives a wipe-and-redeploy
|
||||||
|
# of the Semaphore VM.
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# API connection (defaults to the local Traefik-fronted service-name URL).
|
||||||
|
# Override semaphore_api_url to point at a specific instance if needed.
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
semaphore_api_url: "https://semaphore.local.mk-labs.cloud/api"
|
||||||
|
semaphore_api_validate_certs: true
|
||||||
|
semaphore_api_token: "{{ vault_semaphore_api_token }}"
|
||||||
|
|
||||||
|
# Feature flag — keeps day1_deploy_semaphore.yml deploy-only by default.
|
||||||
|
# Set true to also run the configuration pass.
|
||||||
|
semaphore_configure: false
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Declarative configuration of the Semaphore instance.
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
#
|
||||||
|
# Top-level shape:
|
||||||
|
#
|
||||||
|
# semaphore_config:
|
||||||
|
# project: single dict — the lab uses one project ("mk-labs")
|
||||||
|
# keys: list of credentials Semaphore stores
|
||||||
|
# repositories: git repos Semaphore can clone
|
||||||
|
# inventories: Ansible inventories from those repos
|
||||||
|
# environments: env-var bundles
|
||||||
|
# templates: task templates that tie everything together
|
||||||
|
#
|
||||||
|
# Each list element has a unique "name" used as the natural identity key.
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
semaphore_config:
|
||||||
|
project:
|
||||||
|
name: mk-labs
|
||||||
|
alert: false
|
||||||
|
max_parallel_tasks: 0 # 0 = unlimited
|
||||||
|
|
||||||
|
keys:
|
||||||
|
# The ansible-vault password. login_password type with empty login
|
||||||
|
# — only the password field is consumed by Semaphore at runtime.
|
||||||
|
- name: ansible-vault-pass
|
||||||
|
type: login_password
|
||||||
|
login: ""
|
||||||
|
password: "{{ vault_ansible_vault_password }}"
|
||||||
|
|
||||||
|
# SSH key for the gitea deploy access (clone the homelab repo).
|
||||||
|
- name: gitea-deploy
|
||||||
|
type: ssh
|
||||||
|
ssh_login: git
|
||||||
|
ssh_private_key: "{{ vault_gitea_deploy_key }}"
|
||||||
|
|
||||||
|
# SSH key for the universal automation account 'wed' — pre-baked in
|
||||||
|
# every mk-labs VM template. This is the canonical user Semaphore
|
||||||
|
# uses to reach the fleet.
|
||||||
|
- name: wed-ssh
|
||||||
|
type: ssh
|
||||||
|
ssh_login: wed
|
||||||
|
ssh_private_key: "{{ vault_wed_ssh_private_key }}"
|
||||||
|
|
||||||
|
# SSH key Semaphore can use to reach the fleet as jarvis (admin
|
||||||
|
# account provisioned by linux-baseline). Retained for jobs that
|
||||||
|
# specifically need jarvis-level access; the default is wed-ssh.
|
||||||
|
- name: jarvis-ssh
|
||||||
|
type: ssh
|
||||||
|
ssh_login: jarvis
|
||||||
|
ssh_private_key: "{{ vault_jarvis_ssh_private_key }}"
|
||||||
|
|
||||||
|
repositories:
|
||||||
|
- name: homelab
|
||||||
|
git_url: "ssh://git@gitea.mk-labs.cloud:2221/rblundon/homelab.git"
|
||||||
|
git_branch: main
|
||||||
|
ssh_key: gitea-deploy
|
||||||
|
|
||||||
|
inventories:
|
||||||
|
- name: production
|
||||||
|
type: file
|
||||||
|
inventory_file: ansible/inventory.yml
|
||||||
|
repository: homelab
|
||||||
|
# wed is the universal automation account pre-baked in every VM
|
||||||
|
# template. Semaphore uses it for fleet-wide jobs.
|
||||||
|
ssh_key: wed-ssh
|
||||||
|
# become_key is Semaphore's sudo PASSWORD slot, not a second SSH
|
||||||
|
# key. wed has passwordless sudo on every host, so reference the
|
||||||
|
# built-in "None" key. (Semaphore rejects an SSH-type key here.)
|
||||||
|
become_key: None
|
||||||
|
|
||||||
|
environments:
|
||||||
|
- name: default
|
||||||
|
env:
|
||||||
|
ANSIBLE_HOST_KEY_CHECKING: "False"
|
||||||
|
ANSIBLE_FORCE_COLOR: "True"
|
||||||
|
# Semaphore runs ansible-playbook from the cloned REPO ROOT (not
|
||||||
|
# from the playbook's directory as I first assumed). Path is
|
||||||
|
# therefore relative to repo root, not playbook dir.
|
||||||
|
ANSIBLE_ROLES_PATH: "ansible/roles"
|
||||||
|
# Collections are installed by the semaphore role into a host-side
|
||||||
|
# directory bind-mounted into the container at this path.
|
||||||
|
ANSIBLE_COLLECTIONS_PATH: "/opt/ansible-collections"
|
||||||
|
|
||||||
|
templates:
|
||||||
|
- name: "day0_linux_baseline"
|
||||||
|
description: "Apply the mk-labs Linux baseline to one or more hosts."
|
||||||
|
app: ansible
|
||||||
|
playbook: ansible/playbooks/day0_linux_baseline.yml
|
||||||
|
inventory: production
|
||||||
|
repository: homelab
|
||||||
|
environment: default
|
||||||
|
vault_password: ansible-vault-pass
|
||||||
|
arguments: '["--diff"]'
|
||||||
|
survey_vars:
|
||||||
|
- name: target
|
||||||
|
title: "Target host or group"
|
||||||
|
description: "Inventory target (e.g. figment, semaphore_server, all)"
|
||||||
|
required: true
|
||||||
|
type: TextVar
|
||||||
|
default_value: "all"
|
||||||
|
|
||||||
|
- name: "day1_deploy_semaphore"
|
||||||
|
description: "Re-deploy Semaphore + PostgreSQL on figment."
|
||||||
|
app: ansible
|
||||||
|
playbook: ansible/playbooks/day1_deploy_semaphore.yml
|
||||||
|
inventory: production
|
||||||
|
repository: homelab
|
||||||
|
environment: default
|
||||||
|
vault_password: ansible-vault-pass
|
||||||
|
arguments: '["--diff"]'
|
||||||
|
|
||||||
|
- name: "day0_linux_baseline_check"
|
||||||
|
description: "Dry-run the baseline — shows diffs, applies nothing."
|
||||||
|
app: ansible
|
||||||
|
playbook: ansible/playbooks/day0_linux_baseline.yml
|
||||||
|
inventory: production
|
||||||
|
repository: homelab
|
||||||
|
environment: default
|
||||||
|
vault_password: ansible-vault-pass
|
||||||
|
arguments: '["--check","--diff"]'
|
||||||
|
survey_vars:
|
||||||
|
- name: target
|
||||||
|
title: "Target host or group"
|
||||||
|
description: "Inventory target (e.g. figment, semaphore_server, all)"
|
||||||
|
required: true
|
||||||
|
type: TextVar
|
||||||
|
default_value: "all"
|
||||||
|
|
||||||
|
- name: "llm_inference_multimodel_stage_models"
|
||||||
|
description: >-
|
||||||
|
Stage additional GGUF models into /opt/models on astro-orbiter via the
|
||||||
|
llm-inference-multimodel role (--tags models only). Idempotent: skips
|
||||||
|
files already present at the correct byte size. Notifies the
|
||||||
|
llama-server-router restart handler ONLY when a new GGUF is actually
|
||||||
|
downloaded. Does NOT touch Phase 4 (verify) or the legacy
|
||||||
|
llama-server-qwen service. Safe to run repeatedly.
|
||||||
|
app: ansible
|
||||||
|
playbook: ansible/playbooks/day1_deploy_llm_inference_multimodel.yml
|
||||||
|
inventory: production
|
||||||
|
repository: homelab
|
||||||
|
environment: default
|
||||||
|
vault_password: ansible-vault-pass
|
||||||
|
arguments: '["--tags","models","--diff"]'
|
||||||
|
# Scoped to --tags models:
|
||||||
|
# Phase 0 (discover) -- skipped (no tag)
|
||||||
|
# Phase 1 (models) -- RUN (idempotent GGUF staging via stage_model.yml)
|
||||||
|
# Phase 2 (systemd) -- skipped
|
||||||
|
# Phase 3 (firewall) -- skipped
|
||||||
|
# Phase 4 (verify) -- SKIPPED (collision risk: verify.yml would start
|
||||||
|
# llama-server-qwen on :8002, conflicting with the
|
||||||
|
# production llama-server-router.service. Excluded
|
||||||
|
# here deliberately. See t_730f9584.)
|
||||||
|
|
||||||
|
- name: "llm_router_update_unit"
|
||||||
|
description: >-
|
||||||
|
Re-render and reload the llama-server-router systemd unit on astro-orbiter,
|
||||||
|
then restart the live service so new args (e.g. --models-max) take effect.
|
||||||
|
Drives playbooks/day2_bump_router_models_max.yml. Added 2026-08-12 (t_33acbb2e):
|
||||||
|
bump --models-max 1 -> 4 with full VRAM budget note in host_vars.
|
||||||
|
app: ansible
|
||||||
|
playbook: ansible/playbooks/day2_bump_router_models_max.yml
|
||||||
|
inventory: production
|
||||||
|
repository: homelab
|
||||||
|
environment: default
|
||||||
|
vault_password: ansible-vault-pass
|
||||||
|
arguments: '["--diff"]'
|
||||||
@@ -19,6 +19,15 @@ terraform_server: "infra01"
|
|||||||
# Traefik variables
|
# Traefik variables
|
||||||
traefik_server: "lightning-lane"
|
traefik_server: "lightning-lane"
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# JARVIS automation account
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Public key for the 'jarvis' user provisioned by the linux-baseline role on
|
||||||
|
# every host. Public keys are not secret; the matching private key lives on
|
||||||
|
# the JARVIS command centre (carousel-of-progress) and, when needed, in
|
||||||
|
# group_vars/all/vault as vault_jarvis_ssh_private_key.
|
||||||
|
jarvis_ssh_public_key: "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAID5sym5ajFvDyzw395BkHv7qVb66XPTx/OF1p19MGuNo jarvis@mk-labs"
|
||||||
|
|
||||||
step_ca_principal_mappings:
|
step_ca_principal_mappings:
|
||||||
- local_user: wed
|
- local_user: wed
|
||||||
principals:
|
principals:
|
||||||
@@ -30,3 +39,9 @@ step_ca_principal_mappings:
|
|||||||
- ryan.blundon@protonmail.com
|
- ryan.blundon@protonmail.com
|
||||||
- ryan.blundon
|
- ryan.blundon
|
||||||
- ryanblundon
|
- ryanblundon
|
||||||
|
|
||||||
|
# Leviton My Leviton API
|
||||||
|
leviton_email: "{{ vault_leviton_email }}"
|
||||||
|
leviton_password: "{{ vault_leviton_password }}"
|
||||||
|
|
||||||
|
jmri_vnc_password: "{{ vault_jmri_vnc_password }}"
|
||||||
+423
-305
@@ -1,306 +1,424 @@
|
|||||||
$ANSIBLE_VAULT;1.1;AES256
|
$ANSIBLE_VAULT;1.1;AES256
|
||||||
33333438373661633337383161343862383963623736636136653339363064386538386437323135
|
31393939323063366635653130356131666436323762303533333634333166396337383133616565
|
||||||
6436666330363032616365656434356161396530363363610a333864313064633232366133366232
|
6134333735373036313732303663376130653536633031320a306634646132386335633431336263
|
||||||
37316636366334346536663337663065303635626638666264666435393933343832653061323237
|
32346162326338643665386432393464303165613930306636336136616239633137336563356564
|
||||||
6663333736386636350a653931626665346234323832393334373563303130626262646565653231
|
6536633364623763370a636563646435363930343838383166336438656365373535326666386432
|
||||||
30326263623965356639386438636531306430343239313162383065386135653534636134376333
|
30353534376235626238616662356634653132396138333163343736333631636466343035393337
|
||||||
64616432303732646535643530353963363734663538393539633034326535643539356561656632
|
65613837643733353664633262323262616331636533306561623364303437613136336238373938
|
||||||
36363330346131393262326561356631343631356434666264616134643136646238376336373665
|
64353862616166303339613430646534356237623733613035303066623437666261306130326366
|
||||||
65346361636435316437353235393263313766623438336662353532306463353134366435326364
|
66323331336636316566363532316463346162313239646431613865646462383432316363393661
|
||||||
36613865343264616364333631353238663238313338333232626262313637633662633163366638
|
38373837353764633435303335373639643431366137373930373464336463376136306263636163
|
||||||
61323166393739656536656435336538303439636561363961353832313431666432393463636537
|
61616632326530643531383264323565646466633963663732653561333430343162393035386330
|
||||||
62323939376265353330356334303334303532643136376531343765613738656562386665336132
|
36323566666264646631323939333461656237643736656430346434613566636663663165343665
|
||||||
36346232313432396431666535663362333332613037623531636135376439393936353261653863
|
35353239303433376635646237653739396533626538633332326462393838356262646430383138
|
||||||
65373061316461303866363338376131343736323933383636626338616431656533363833663266
|
38633266623464643463326563613232333361336162356561623265643130346537326238386134
|
||||||
62363935313262393733333566386337633630666332353263666462373164346362313034636239
|
31653061376334663534643130323032626232636565396466643664326263643730306439663337
|
||||||
33656462396238343065613965613232623132343562323364653366313231323531326364376631
|
63323630363863356561316139343766376132343832663266343232386133383135353861363231
|
||||||
65643961303862653030343364326533356336393031636437393465636263626236303633326139
|
63643763356361396166643262353866613235383033353562363761363539313334316535653462
|
||||||
65643432663037333332346261323663613031386563383533336538383133373332343363326530
|
32613139666234646238613837636462653532613631333332386339636334616535326333626431
|
||||||
66643231666636366435623639643166333863376533633537363364396663363732333932663333
|
61616432336135363536316137616364306337623966646366376233633437363631306662383565
|
||||||
62333239613264353233303064333931326236396538323130353061366139623362393734323434
|
66626433316135353339643235633933626563363334356234313333356237666665393931373837
|
||||||
36343537393363343861633131346561353637646336313233376162656561623362653565623339
|
66353535343339343631333662383238343930633630333133656236616335663439393865356564
|
||||||
63386337613461343534643964323932356661383436303966346339386131336133643132376330
|
36633334643739333035646139666630396239626230613264353237383830653461613634303532
|
||||||
38656535353335303966636235643666306336396435636434363733313665366234393032333065
|
36303730643632393731373037306261613037373630643137646166316136376633353865396335
|
||||||
37633231376134636435343233363032666231666134623365653238373836326237373831326262
|
34663233633431323233633038343961626538626161336533316339343539643764643531663666
|
||||||
66303234303164303961316166623062616139353264343864363938313733653563663661633535
|
34353234346362346263656165393538346435663465386164336465313739656334383339633661
|
||||||
37326636346435626362336437666364623264363565653935336438386262376663303230313265
|
31613562653062623064353666666564326339626463323435653763366330393463363935313834
|
||||||
62663665666132313436663330616230383235346333623563313262376530356535613263316436
|
38646534343261636362633464373034373432643438346364306163656164663762373133366239
|
||||||
35313766363763386234333733636464326134633136346532346632623534646365623136343363
|
35393231323337663633613936653534356361623865636535346263396665373266616231326362
|
||||||
30316435613031333036383835656230353430636135343961356363613139353763343233633834
|
39393061653563333562313639303031366236336464643864613939373265353961363739353130
|
||||||
38656431363139396535653565633631393462316334666464333839343035616531643466643531
|
65323761346363336663353763633833373633666661353032363961393834366631616439316161
|
||||||
35613733373331643961353830376266376433363938373563653833343464633465663766333066
|
66316438316135363038333831303563363137336439313933393333626261616535373932316231
|
||||||
34633364313762633034633461623232656537653762623532613332386132333365383062653136
|
32333131356330383239336432663761626265313266636233373363343031343339396362316535
|
||||||
63323234626266336462333534636236653230343530336532653831313339613531343731313237
|
66373234666536316533616635663837363361313862386364343932336430373934613934383062
|
||||||
39653737663665373361326433643364656434393838326339636238303964366336363961653366
|
64393835303235303835363633393430386439313536653835373164663064383936363335393535
|
||||||
36643938633635313432663765316130326238306163346566313062626439626263633033623731
|
32346265346337643865303030393234306565386137326637353430353633643939666639636162
|
||||||
63323532346366653238663931653334613734633963363632643462316130393138363436666532
|
33616537333266396535643536346530613637663464626238666464346661653235623064323763
|
||||||
32373833323330356164626332646232623031326365653765336261323661616137373732356164
|
37303839643137376438376237323162663636613431306130373562323739343636303936623434
|
||||||
63383633353764643233323430333233306337623834353934643864636339646239636430316166
|
39643764363065363231613065366232343638343461326635303862663834386633376262613862
|
||||||
33643030333261323461643031613730343131343830353463313766353035326436306566343161
|
37623662346139623734303239346366633231623937666330326631313637326466363833613534
|
||||||
35643534323763316165343832346433356364343061383036306434386631356537363331303035
|
36636639323563386161313038313835653061613530343538643665663439383361633365656662
|
||||||
34303430393034393763343964613935383739656662643066363633333839396465386231383837
|
62643732633634626139643630386531303634393432636235386333653732336234663738346562
|
||||||
30336331393365346636363732616661633635326364366435366466383639353839343731616365
|
32363832326365383137333566623635376335666134396362343064346131643331666666343463
|
||||||
65326633636263653438343561633632646234316461616666363630333966326230356331373335
|
38633837623337333061373164393330303161373632386139656336323837383637666138663832
|
||||||
31353665626233663433633563623765343431376639316232346666663065656462616438663333
|
38323763343237646138636561363436613063323962393362303630623036353537353061643463
|
||||||
62663662336662346563333935333261626635343764356631356363356362346231306535376466
|
37313863623062653036663733633731623831626130373265326231346363316538643562313036
|
||||||
36393932666662653934626134613065623461303834393231616332363461306534303666353632
|
37623566643636633938353235653364616266653861613362383464346237313031663063646466
|
||||||
35646363333065356631393863396536633838343365343238636332303862306631346639656166
|
31643463363138343037646164316433646232616430353338656237623436376534366635306663
|
||||||
30373735336361653863326331373834663164393863666631623866353338366561326635323132
|
61333166363537386235663563323834336130396166393133313036653631383035336465333435
|
||||||
35306535626564376666623837666435663337613164623966306138353161313239373436346239
|
62336433613235616234376133366563383630613161383830396165646134323139313437613236
|
||||||
36656266323233636233326139326266346464353665323465663666646264613466636132626464
|
38656531333137653966326462613534373830616664326362313064613434363338343564616230
|
||||||
37353762306538643233663338613062353134323832653139663036666337643131613062643936
|
35316461656135336563366637323933363763383165393535383566306332366530623735383034
|
||||||
37633363376365356333353433613839653130323036643737633163336531323032393937333432
|
39663434336266386535616430656566353137313231353839653565663430363638336530613462
|
||||||
39343238396534353330346664346135326333333638666261396463656663323935643337313462
|
33326232613964636231386237643063633335373234346165333336393234666233623038363165
|
||||||
32396137613432623664323134356361323861306230353165663162663732326563626162346630
|
65336139343634303462313335636232363637356437313161393739313966616364333335616261
|
||||||
34626536393962393764393764393234373138656432346332633963393135386238313563353761
|
30366536623663306535656431383534393530666461626562353262396562323638663036393934
|
||||||
34366438353337396264373032336166663937343931633635666166343638386237396333626133
|
32313361333439376563353130653537346438363830346138643438613433323731663631363732
|
||||||
38383766616566336163363931393438366566386565663938356630366430393830653037363738
|
63613738363637613230376337373137656363393261326461313233343466393766623433383338
|
||||||
30666465326266363834653934643434666466326632366463303965303366326364316430366561
|
33333533623838353630366566636661353730313737366333653537623637636138616233316630
|
||||||
32636631663232373163636535366333623261366466623262393631626334626263656534386536
|
31363362646565383534343535393266396465323634653262653931623931613565313932363961
|
||||||
66323833353264623538663232376138346361646362313565333534363535663031643833373064
|
36623161373665393466306161323862303830616333316563653165393736343638613434323766
|
||||||
38313062346339636335633962323933383230623634303431383236626166636535326465316439
|
30353331633039393461393062323335316662366537333035666536313036346266313839613031
|
||||||
38646636336130373763646635386265373065326263616438646565313439613830316135616435
|
38396232666165633437343032663565386133633631643863653539396361623232643532393665
|
||||||
62326430336337643265306261343036653938633634626561333664313035393933646533326661
|
66646334386565383338396461326366393833633037343238306635383663306635356465613932
|
||||||
62626437306432353938356338616462663130646530623636393233373837336138383963323165
|
61326663363634373737336265643836396238373761356665316464626138643063613632663461
|
||||||
35643231613565313434386163643637633130626435376561376235346438303234386637383835
|
65646366336633383765373034373834313731356330666363363535343934663366326465616130
|
||||||
37356238616263646665336435306233396436666664396532373063626162346237376662393639
|
64323533366235313064306536306238666366613839653730373864363861373231633164313034
|
||||||
35373665373638396434353062666430633362653163633639623836346438323632643164653638
|
37313361613666343531663965366239363735643465323763373362623961303063303536663264
|
||||||
62623463343465303236346562386338646536656438633966643430343266313935323630616633
|
63366638313332356164616435346335356536336266646263346538393136323537663464643265
|
||||||
62313531343764343966333439343866613965303036616634363162303434643533366465313562
|
64313730396638353465626330343836313863636666386334313432666230613462363137303732
|
||||||
62393666313838313938356265633531326431333730626632343139666338656465306431636162
|
64316234306565396464633662653831393934356637613139633362666661383530363032656465
|
||||||
66343532346238393464366134656334363964626264623263353537633638346239396539653538
|
62366639383433393861316132323634373366376539636462353663303466383233393830646338
|
||||||
37303339613036306533353132326534306433353364613536316263326363323134333639346236
|
62383837633533326665626161666530346336616436646535663930386462313165653436306633
|
||||||
39376263313431666462383863336638306631663563313364333235333338323364613361633532
|
34636238306636373136303866353832303265613831316236653832396466643934356464613331
|
||||||
38313263353539633662353533646333353262356436353938303036663130306362303935356136
|
36653466363561373065363934653434616661323438353166383564343731316662626264313034
|
||||||
63313234363138383864613664666635613464653765636461383738356135623662313866383036
|
63626638663333303938613636666239316635643931626538633465613465663235383137633839
|
||||||
64626437343465333563346434323762313232643230323336366539326631396463303961666461
|
61633761336665636164616162313838333937353761363635623033363964616137643035333735
|
||||||
61656338643532616337653362636362373837373836666535633762343335623033316264366261
|
61656639656263373535356331373633376463326134363031393765623332326136343163346533
|
||||||
62633137356132306430623537616135613965393737323263343463633839393165646630383331
|
35373732636131303561393462656637386631343736336636323139326234356238336238633637
|
||||||
36616339346534346636396532333836633436323232323364303963313030656330386336633538
|
61306462373633386136636636383137356437653565346130316262373436663838333065626239
|
||||||
34383534313236396461653462306130376462396138303561636331663062303864326238303335
|
31643264346363346237643064646263663931353663613036346663623031623064363637356537
|
||||||
65663832333631613963326639386665643135366632393438666361376334636233336239633837
|
30626336316531313339363937313938393864633733303738393766346537636232326232313833
|
||||||
36383761616364363262306535653065303536363066316431303464373230326436336661396231
|
63373563613935653965653737383438643566623532303939336231333639623834323639316466
|
||||||
66333438376664333731333630383031366237396638326534636532343535303964653436633438
|
38653635643032643431326462383634343235663630316264356431396561363932636136656563
|
||||||
64616263366561653334346138393866353437393037343930623237326231303261383733336232
|
37373466356538366636396130306135636637386632393763333365626339643735616332393236
|
||||||
37646533393439653965386563333232656565663531396663303334313839323361363864396332
|
65303032343831363332646564633861383865663731343632303263636136353962313232333938
|
||||||
61656638303130303433666561646663323139643337326561333832373538306236326538363637
|
61333633633935623365393032656133323434626161633438373766333064633161393434366235
|
||||||
38666534633330653564653066643335623938373331376339393338343533366436333330313165
|
66303566383132313538303637623836623163376665383933336533666530613738303262633333
|
||||||
65366562386366666632653064663637343536313462326562626436356363306134306237613265
|
35356164653063633039363039663934306333313163363034656463646464656436653438323362
|
||||||
32366338643237333739626331393763323934396265383138633035646533353536633866313432
|
39383638373337306535313739376230316166386537383736386163663861653939633338656538
|
||||||
38336137383036373434363530353833653938663035306337643638316463373762613931373038
|
38646431623831353537393835313130623336636535313765633830303164353932336632373131
|
||||||
32373361326136616331663733616133623936663530356566383461336334663937383230386462
|
36353566373662663437613766623434636165616562353938336631666665343661656363313538
|
||||||
38656332613763653339363565613762383735333163633831356364333563363630623666616430
|
35376633373535616163623838616561363932643366363235383335373632626131313063646265
|
||||||
30353237653730613361643233386139303639666137653733353334326530306431376666663664
|
63653236326135616361383339623663373331343735356334363761333766376333346332663733
|
||||||
34633531393261343165663330373961646665396139323762313663376639366464306533623333
|
61643231643465663933623735336532326431623764396136633863353135633432356362633364
|
||||||
62326432623334336166656565656230313063656163636561326632666438633966323930316264
|
37633138306266653339643763326330373637663831366465383035613463336336326533333038
|
||||||
66373866663461616336336264356561373232313737353836646632383438333162383832616662
|
36643961656336626537333161656264383334323063643462336331653663333636376663653065
|
||||||
30636437613163613631623165366631306438643765383263626133653231333361383633363136
|
66613231643363653163633330373039616138306261393734303536333763313530373738313266
|
||||||
36653831623562653838633133646633393038666164346461333531373034356435363336636338
|
64356332396137383966393238313033393934306264373234633132613231393132336665663930
|
||||||
62623464376264363537306166613461396630303039373239656664396564333435303164613235
|
35356364666334313937323931636433636164383562396433316164316232363262363132653435
|
||||||
61346238386233653462616632303337663036626465663361636130333566303337313237626237
|
66656239613163353866306631323961623731623932383265306339366134346666653664343639
|
||||||
65636633316366343064663636383362316665633263633136323563363935346138356635653036
|
37623766386538323763353531613530313665326661356566373035323833333033393364343439
|
||||||
36383835323838366363363335323731333066393334373265653563336533616362633163343661
|
64343133366334346532316439316433346238396639623633373534323338356263643263386332
|
||||||
66326630353537653633316631343332303231373630363635623136386537666434383032323165
|
39346339346631333733613064393964326234383434626462316330633031346262616338643737
|
||||||
33333633643064376239346139633664633330323966366430353135616633633465363030386665
|
33353866666532333233313362653765393664323937666435393435373638643039306366633539
|
||||||
36353164623564343934323063313763316566373830643163616633643937323732333561353832
|
36336132383032623864376563623634623461303564326639366361353961366265336563356436
|
||||||
66623364666335316230346665353631663465633034323265666663653866623037353935393262
|
38616538303831653533323332363863343666383537633864356665613139356535666136623364
|
||||||
61623065656637636666383239343661616233396663333038393963366537326136653863333235
|
34646563303636643133386537313038313066303735383437363531333739353166333635333762
|
||||||
65633137626134383763663366396438366634313465363965343830333966373930333134353339
|
37356532376132393862666236303332666262326135663735643663346234376334643966323339
|
||||||
35396538303537316636333339613731623636646230323662613663306537326566656666323434
|
35626437376162366638373235366366363166666438363964346361336361623234353337623062
|
||||||
65346531623533336535393530373963343864313963666335636334396663393837396665373565
|
39363234663765343866353964393438316361343532623766393964373838323363333633323134
|
||||||
39646138356134313732666633663061646330643438393736653433313238373135656636643337
|
37356263303564303534656338323537303965333138326636303138636534323461633837646462
|
||||||
39396362383363333434376336613933613438653636663334336337653633613433623336623461
|
62373839396138623739346466383830346535663534313265393761376135653465666630626232
|
||||||
32373565306435646438306365343465653863656434663937653938393839333739363639326536
|
39316337306161356239633435663166336139626232653261323463386363616636353138633133
|
||||||
64303534383961333333386237366239386330386533343939613664363439373135333731393739
|
33303134646130643261333630643038343637636132323930363638623266376263653561306634
|
||||||
39363166306636333766333332393265613133356262356666343039666237663664636266626664
|
66386363656233386639356462643234353464323239336464646236383537306539356662373865
|
||||||
65316339323638353333653631363365356562623535666235313234613236326130616261663830
|
32653865383932636230656662333530373663643363656166636535663862616330386163613337
|
||||||
34663063626539363734313562656233656131326265626637353239636638396564313561383761
|
39623864633435313735386163666164646335353562306162346339326231366566613735353033
|
||||||
62663638623135343333316464346236353364616239633566393039633339306334623234616331
|
32373762313636343761313235306234343639613463616263386130636165393636383662643739
|
||||||
34366435663938346335323932633330366639653636336636373562306561656536653363366233
|
65303537393437373866316535383066363732366130646533663062623361623565653138383433
|
||||||
39383064623435356338636335343662343435336564363965646439393964323162363736346637
|
35313335346236353363323434653434333432316531393433306435336238666561613161643531
|
||||||
65323765333364353831396433666561376437333834313334316165386631616332633533666336
|
64393732333932623266643938396132393235333030373133386638643831633138613835366530
|
||||||
37313533623535313934393230353439363231623063663961376537393638636237623134323337
|
64633933353465646461356465633239316631666264353530363938343732656233323339633061
|
||||||
30393032333530316330333736616463633262616631353238323933303766646137386465643366
|
63636364323762633639306336613532333935633132633239333161343933383030663539623732
|
||||||
33356665396437623732373437373537303034353431353031313162323730316566396238653038
|
31616365323265373461343961313436613436633061356630656433646361373464373962303534
|
||||||
30366234663037653736353137376264363934646366353761323364663538346662323934343266
|
63643039313565316461386230333964366537346162303838633133323339323636356430373264
|
||||||
30373662613461663561623466633939396439653663353365346133623933613462623231616562
|
63333364383363613637333463383238303734323130623437333262613763663535303563376631
|
||||||
66643738643661643766323266626266313330633936313964366536323263373666303130623738
|
35616133366439313362653763643135383061613362306533353638633666396266636337323031
|
||||||
32323230356665323439646532343930333936373536626466656566363161646663616266326133
|
32653435653639663335333137373964393431633261373436653036393366633639646639643734
|
||||||
32393137663562613531323832313565346632303131646432363961613331346636653830323136
|
35343639616637653464663964383961636565613363366561353838663464646636393164626162
|
||||||
36323436373964313737313131346131353630636561636639316464323666636336656265343565
|
63613763386262633936646466316531353164323036613539343938633830626361376135666337
|
||||||
65303936353165326137613638366532303265356537343337656165366663383961643134656435
|
30373038656339373665613833383439363131323562343435656633353266323762323764633336
|
||||||
61383565306265333939613561613035616663336361396536343939343761663833346134646365
|
66313561333066626634643531613930316664373434363365626337393833393835656262343662
|
||||||
34323233666439623436323261616432363838616437386138393735383364393164646638373630
|
66306138383962326366353832306164663561353661323538653861353338633935636630346135
|
||||||
33386632346239383037633132636431366264383633333365306338333661303662363533376339
|
65343964323839616334363430323563343463333832623766633364616136393934666238303130
|
||||||
62633663366362303038616666336335346332316366353136323666346531393938666236343163
|
30343662303736626639613034316336313133633630633638356339323831386238373832666232
|
||||||
31663665643839313439663839353431343061386465366331663637373532613266383065393639
|
33396162666134366439626564333634313666376138323039376636346436343031633361663130
|
||||||
62613565626135363133623261333061373738633333623337396631356332643039306638303434
|
66646364646235353531336132636339613138336332616165376138313764346630333233613332
|
||||||
65663762373630323263333239613939346133626534613632396433376234663636363062656537
|
65363432393532646663333465363231363535343961326631393565336363333362613730353733
|
||||||
62386664343462346334663662663865653766373738306438316533643962356136653565373761
|
39343862636131346438386165396334313230663461336264396666323962643561653139323664
|
||||||
62393437326138323065396630653838326138653865643937353431656137393732346361353734
|
66323436663539613832346265633962616531363731376261316463373035626434313731623864
|
||||||
31326634653331353232633061303230393462363065613832303630383237366463363666613864
|
30366561333161303934386562643835373336313530633436326334626537323365663138663366
|
||||||
37643135303034326335326563353064343835323863313134616262386564313235653762376332
|
33626534363365376633626564326266666431626364623832373865343035393963383838346362
|
||||||
36636533646235343138396537623266333566633466393764353731393935306432313266636133
|
66353835393439383966376365393966636131306464616636643035383466303064306635343036
|
||||||
63326362653033613264333139633638643638326532313239646239386332323330306538366362
|
64653738303232356437623937343963313837653931336339396561303864393739356135663664
|
||||||
37646432363535396161336465376363343430333261396536346464356135343462663462613136
|
36656163653266613330396236633566366331363236643861373338336562323066653766346232
|
||||||
36666238633663326230373834303431336566366666666534343537313635366537396262656236
|
62386339343161383732353838353764326264376432313865313534343734326538353364623535
|
||||||
36646639643730393134613662383238623835626230313833653932303832323366343765343434
|
36376535623834303038396139343739353131376338363738646564363931653634323639353331
|
||||||
34363033323836663035363166313630313062663162313165636138373261386636623831666632
|
37393237623864316433313139376538356538393966663065616131613931616638633536613930
|
||||||
33373962626237666130373031633437653966386561363232363332333633303961323864333263
|
63613635643565386464303065623966623038376338636663303435313764393838626563313335
|
||||||
39666230383332376537313137643635623336316336646537333137633564376432356432326639
|
65353636356330613132333338373764353766353363333838333839633635643935376462393030
|
||||||
61383565313233376435636366366531363462306535636131636163636130663732383161616364
|
30306533656139666534666162366465306163393063633632303330356165643135656433313336
|
||||||
37343064333264663533343739356139353365386565383833363165326536306431393764303632
|
62653237393834356334613038343736336162343337343666333935653635623834393139313230
|
||||||
30653865623566363965306636366530303261616663306433393135656366383138356337383365
|
35376233653937326630393939373365643338353765356239646262633632643161626161366465
|
||||||
36323736643035383231663034626564643235646237623632383164633062326132363331353634
|
64303630333433303631396135343931306363393864663162663538313263313333356262326464
|
||||||
61653761346439326665366565383534393635616365353361353863363763383664303166383434
|
36383962616163356166636137323230623262343636336364376366323238386663303336653738
|
||||||
33393732313837373336616564343864633330663566653933356237613538653366663838383132
|
61393138396333623738333766636563623834353737333134303733336165303235303635373361
|
||||||
33303437323438313837616134616466626562313262653866313034383764656566373331343738
|
31633035626334313336373733646364643333373063613063636434383037323931383466633164
|
||||||
30613062303630663365636230396231313065356662376163353632613564363066316239636434
|
32396233633233646630333037393635663733373664626665653533303535633034636163643937
|
||||||
66356535386263353737383838653538316366343935323337386561353533353161636538646363
|
37613537616137303261366533656536376437353839303439373939373764323563313363396134
|
||||||
63643739376366326536333261306263653563353331393133323964653764373932663136316335
|
31326632663664626364373133346363623239313166653737646335633833393838356131666233
|
||||||
36333535626231373864316634613366353535393932373039646161646466363663626561373033
|
65613662303338306638623462373961633338346130333463633465373739323436306232333731
|
||||||
64333133353931303361363466346666376431363336323166356162363537633536336638653838
|
61666237326631323434633063373338663961663837653038326233636666336662303737363935
|
||||||
35323562653138393833383130353232616564393738326638366565616233633634336438303632
|
38613663363430323135346566306664633930656434653833323539323266373931656131623933
|
||||||
30353765623565336330386335306162336662643466663335623836383238316161633339373137
|
64613763643664633263353162366231646262643164653437316336343438386665633562366334
|
||||||
32393165323735643034633464313337386362363331353432363233396538393835383933313637
|
39383261383265323239306266323839326566303666623462666236616266626439356266303134
|
||||||
65656330383732633537646361666439303266653165313233636464313964383639346635376538
|
61306530326265623132656662653335393962396135356561396231393831653331313765306161
|
||||||
64633861623439626331643431326336646135656539313836323135373862316438393237663564
|
34353064663032343438316163633333366266363839653662326238336631623863663937316266
|
||||||
31373135356135356662336265633862343435356530393835376430666566653036373338636332
|
63303936663666326539633138616263326266613534303162346531396333313930366466373161
|
||||||
64663230323361356262356537656262396665663538386664363735646234306231613339636338
|
62363064653737383264323235393935656534313830653137383834323363663237356230383832
|
||||||
34366433326535353965376236643661646339366566663531653864316533356466653864373633
|
65363139633961663063633936323339363839663361383361613864343035333135633038626234
|
||||||
33363330333765373662646634326236313434383433653563383436316635353461386662646165
|
65633662343264616637386463656261316631303536386236393635636430383563383232373938
|
||||||
31626566616163373137326165323066646535663766636265386435633965326165303831323633
|
34656437343633333438666461343665383066626230376233373236663561666135663433623137
|
||||||
39613139623835316165326138386431383530383035653931616334353235636138303761383037
|
30343639306333663530646635366166626432336530373363333131383338363966303639363765
|
||||||
39336163373332346365333935656563343939623335313461363138656239666263366236663464
|
62623537343732396264393933396366376634626239363761663366636433336630393036343162
|
||||||
32303732663937363964346639323236623166373334386239613564643834316536363634326461
|
64653339633131363035666532613433613735313835616433316665386133623762396363626136
|
||||||
64623939363635613863613065656363303734643766306564326437663037623839303734393036
|
64653333613561613362333531343961343237383564386239376438613935393066383138613637
|
||||||
64326363626562363934313930383766383462663766336666663338653765656137393362643366
|
38356232396432623063373138383231383565633264356562303031663538616333363038363264
|
||||||
36326336323638393161353464396637633566383262333234656233653334623131323532376637
|
32303030633037353130326365386332623634393139343061653136326133653632613330373836
|
||||||
62613064626532616631646232386631623839326665346431333232333463373031316237363462
|
61363166393766373232633637373265393539316134303961336561373534343137346434663462
|
||||||
30643731653666643331643839343865646437613135346363646131383262396134376363303335
|
31663232363638373939626432316232646338633863323031646635623735303762313030626664
|
||||||
34303164303236383139326264623462363062313139653465346435336163653863633764613631
|
34323361333431646636386132363237366636633332343434323765323235316134386636616231
|
||||||
33623666316530353163396539323238663935643764643939333966336137353034663164643733
|
31333564383739663537663131623066313336333630316336303130326531643539346236326131
|
||||||
34393132323339626331626532643266336435653636353930393738363134353661653636643263
|
39393034326661653763343761653162666561656564356232383436323864623838363730616566
|
||||||
30313138393263383837333438356463636162383938396137363035646433663932613066386138
|
34366464353765313663646430656539663764363562356336373634646232383338343737326662
|
||||||
37316535373939326131643930353435383232623366393630663463633233393232373730333631
|
38393964643261376562336432393863643733656438313462383161613730656235666333643233
|
||||||
37623837373533383462323431323335316231356436303239313535633837353931613730303363
|
31333633346333663563363730376164363363356264396334393065626165353834623139396235
|
||||||
31613765626466636636613366346166393766373834643337353764666532376335376139316138
|
32353734316137366131383935313136313337346436663735353331393030366330623937383132
|
||||||
38646133643736636363363434306334373933633264366530373534666637393835366266306633
|
33366132653534306661633765393833656534316533373163323333613839616165356636373131
|
||||||
66653966613136653936313732396366323830376236626530306139333030323966383035643733
|
33656534613830656532333533303730323539326439663665363061636431303431373662346462
|
||||||
36353833323539393136303035393866366563323430636336356639623734656135356566373062
|
36323265343939643936393066303065633637313437613832303062366334343139643864313264
|
||||||
34666433316139316664643234623530363732373338623162363636303463346463323131333065
|
63653665316638376433373861663630316439636130626333336361316165383535316466626565
|
||||||
64656566353837336266386233323439623237366364343635306137663038326434366531623062
|
30306662666537623963646432323262386132386130303335653634643436343334333130306261
|
||||||
64613365323339613465326464653965613439653766623762363139366264663765363862323839
|
63343666363536616236346637633632353839356636623066386238353833623565363932313766
|
||||||
63346539323961343532626465363266626234363964313531353662636635623165376130616536
|
61653161353835373762333034613563663633353634663562306634373938366130613831336339
|
||||||
64363361383766636333626366616531343833633033643965626435313130653938316430313532
|
61656265363662333536303633373233623436616238383463333764643362646532393630646664
|
||||||
64363731633139383236326231653434663132313463326563393739393132663765396337643035
|
34653765613362376238363163326433623963653334306231343135636230396562303662383738
|
||||||
32373963393830356362366130376135353935396631393533333430363531636234333832373939
|
66366531656562333533653638316336323365343063366332666436366161343730313433633362
|
||||||
36656233343663623262346337323034653036373432303266353333626434353137353939346665
|
61393461396162316231613265393932343866663537663333623035626635316466326664666237
|
||||||
37633432303162323538343339643635636464353333313063363662663033396630303162333639
|
37386661346634323438363938656339636434383931613931613262386532646466393333616637
|
||||||
31633537373364666234653938633461343738333464653736316331343038393333643936646462
|
35336563633164323535326530393134383634363461313366626139616433393935376164646661
|
||||||
36373232373962653031333730363166393463313232616631383233386533373464366465623335
|
30376638373565633533343730623665303438363361363065373166383662616134653066333132
|
||||||
65393462353638633931353331313233356230303565313030663739626230323766666466326339
|
65636233373934393336383631313932326266366362393036383434633333333333613937636464
|
||||||
35303361383065353333666161306433383139366439633730666364383130316637633464646336
|
32316462373532313934303961616138303862386537333439313065393630386637303161393330
|
||||||
66643065303934663765623233333261313939373236396136366566306438626439393163636430
|
39346137326338386634313838306462616263353065616639323532336531383238666662313664
|
||||||
30656334663361396230303239663338373664346362623934313130343064353435626439356562
|
38326163653663353332346631376461306663353631363661346337663266323166643062633132
|
||||||
35653638613037656133313765313165333066353732363361386234353635626563323932356237
|
30393863303130643534313035353631636631336465613738663361626630656561386236326661
|
||||||
31363333326536353536323931643739333764323637356164663566343563633761333462383735
|
38643630393963333036393534373839616236646466646433313034353163376634393038643838
|
||||||
66383134646139373130386366316532656139336231303931656265636130643130616531366530
|
65356636356265373339393765613164343834383762353234373831613264356134643739666337
|
||||||
62383132643236623835323362383866613765343762333536333365336338373264633130656438
|
36333162353239313437643336636438656266646536663939333765633862616530386538643935
|
||||||
36343331666431326530626137333665623836636136303031333965356366396239396534663263
|
61323864323632626331383461613534336534666533376566323936363031343537363432396431
|
||||||
35343730303534313830623430666566386564653036356635623038303133623231616635396463
|
61643339643038353432366261663633623631396463373735626433623032626333653939323736
|
||||||
65626137633033663631373366373238353766323533643462396562633164633730633135396266
|
64633336616536393736636361636238393439386165623039373537326462633332343039303339
|
||||||
36316362353964306463336237383232306530613539653462326137383938333638353038396132
|
37376339623837323461353739346266623334363439656133326130336563396338363963306433
|
||||||
66343265643162363735663235353161393732326530373735363662633165316265323065396163
|
61656531636232326539336566616536613836353633316666643633653131343161626332346334
|
||||||
31663761303637616566396262346238366631663562323566323364663464373930373831323630
|
65363136393539393039653134353734333964613533323061643563373332303935653837356264
|
||||||
39333165336264336539353634633936396561626363353466303931343436306636356663346438
|
38396136313265333063643937663461633438333039303234653662616666313732393038303937
|
||||||
64373561666638656439353964626436613164643663336336333337393332346132313830316430
|
37336133333030643133333539613538373461356131653262306630323734663532333932383163
|
||||||
37336139333539316639646337383737373530643533336133633135333936343165303764623366
|
39643838366263613062316331373537616137343035666130333263663361333730306233663432
|
||||||
35346432656263396439663635653066303861643938633033393334336336396133626237336432
|
62313539663138326239353932336364383337636564616466633830353030323664303961383865
|
||||||
31393061653839653964613239353336653666366163616163616230396661313233613934326339
|
37366635653939626238376238613730663333343664393966663461633866366632636630333139
|
||||||
36333733663032613633613037343337646237666565316239303231313163383264376636336338
|
65636361363339396337663937656533393639363336333930643530346361313832663864633239
|
||||||
37656532373634383132346163316337336534316465383531316465353861633062336235376631
|
37643439306631353263306664393938633139653633386466306563663333396663393266616438
|
||||||
33333963313730653164313866323461353334653231333762336232366434333631396135333466
|
31663963626564626461643038653363386636646537626561633464396535323666336264336130
|
||||||
36643362653137323934323966303734316334306133656139613763336431323236643264663530
|
63653238366565336431663365373436323938363764366137353034663666383537346264343136
|
||||||
38633730346531396435666530316563386566323737343766653135386537393165356264356534
|
30613734386432356536353431653562363738363762333632626630303738366437313431656365
|
||||||
62323962306332393063313062313230333334353833393362656166353638323366353934656263
|
66653830663236323865303131373335376630333234646232353731633764643935653631613363
|
||||||
38633531306438663134616262323332323338653361356336353962376331323537623734316532
|
62343063623133333162343066366232303233353565373739396466376239373163393065323132
|
||||||
35306434383336633436656437663765626530626535383464356532613536356533646332646135
|
32643636396532363531356530336563626164383164306161633166353262633433393731346631
|
||||||
39613030323432643161366363313262633261366566613931303663636262353466313933303162
|
31383730316130303137643438316332353132666436333232646435313161663333396537366163
|
||||||
66373535353934626135326439653630303437666535396266303532626636613563616633623237
|
36633063383238353665613333643262383365396439366265653739386264353436653137343239
|
||||||
38623938323137393065616136376663363234633735363264356438353534616338393832386337
|
61316465313835643565343733643330326236303463633032303133343662663834653462343837
|
||||||
66663339313062613766666435626364353935643932633233643630323464336135336339376437
|
62333334613066383537623838313565353430323737376237666164326537656430373032633637
|
||||||
30323536373639343738613463613466396335626339343135306666663931656564393664643761
|
32626264353461376536376137653433613035346264363332393462353562653537626262656663
|
||||||
65396336613465313035396134636438636134316236636566333031646666383939383264303437
|
65366237373363383738666134623638613138613962613936353933313061376162396532653635
|
||||||
38656337326233363866336363363161333236326137393465633935626165663136316661316131
|
31663932343936313831313636316234616130336361653533666431313334323235326565363131
|
||||||
66393764313130373766386235663134376239323037373365333730643336656532316434663265
|
33343630643764616230376434626234343463393634633534663361373465396566313862633834
|
||||||
35646664383338326366386536616339393938336539373762643839613763323434363037326330
|
39353964376434633130656535386239373963653832643838313833623839353866386531323062
|
||||||
66353738643735656165396138343262653563353934376237366564636638623630393238373530
|
63633665383935663965303830623563613734313034653139356435663733393836353834373435
|
||||||
39336335303564616232393165653639326166333536343966353933633365326539383632646639
|
32333636363937303039323065653134623438383730326262313065633265363866363435623336
|
||||||
37636238376137646239353731343933346562613630656130653865633834626363656231373162
|
33623536623432376365663264386539303363663463313035356164323038353264363862353964
|
||||||
65333662653962373139633466383834626566336234316161633038653137393266393564376439
|
38316235373434393964616233346430356463383230393730343437666437343663393263376262
|
||||||
62343365666637396639326438326631613664666662653935346230316632396361663038663239
|
32393861363264633130656266633261623130613362663537373332626230316161646539323264
|
||||||
63336335643665353162393330623635663839666162333561376265363330383530653733333239
|
66613533653633633262343134326434336166333634323034623738383539373230616237363565
|
||||||
37373665646562343562313764386534663239636130646564333433313661363338326439363865
|
65393765613134393465376435626263323633396238663630373564336136386366326631373530
|
||||||
63353064613161366461383862623363333637633430376361366566383332636634646630363139
|
61633738376236343863363031343835303931363936343364656136376330303566633962323232
|
||||||
65303139396539323336313666336362626339326666343061303431356361343438313365353431
|
37313266393463373065636466363665383665663362303137613138643530393137613761653633
|
||||||
30303266363664373233303231346166643839343564306363613236316665306437333636343131
|
36373363336430336366363136323030386537343962623361373265393132636130373464663335
|
||||||
61303234666664323138376335623639393939633836353664343232316630393263323233343366
|
33396437663064363634363132363038663438396233303364646266393931383862306464366336
|
||||||
32393736336166323166616139323066613062646139656236343233623630616262343034383631
|
66616131643662393862303166326165396135323765616366333330316563396161366561363132
|
||||||
61653662383537646364363764353335333630353431633534313731633265626263303863326565
|
63373635613663366232363238386331316461616636663439386434666165306330366337356534
|
||||||
37616534303164316162353165396236656565303532326235393237366434323739633662663261
|
65643662336138303335623765386465643561613039663536363734616264333431643337323437
|
||||||
33383635653734303233356438636132343731383439623463633732373833303339353662386435
|
35666533646432336165343761303137633130303164386166356337656337356437613862336132
|
||||||
63316138353766303962616435383138373739383835353662613666356565366237353932393263
|
30636235643532356236623762363239313163613432636466346538343062316435643735393331
|
||||||
34326561613234356537343234303166613534356134643766383332646263623430653632386365
|
66623331626566303535623631366135316238346165386430363062383138373132656633633939
|
||||||
61376165656366366532346465343932313032643163313362373633373066653036346238343938
|
38643765323636393932646363313265333637643535333762633939336162623435346664383231
|
||||||
66626133306163353966386662363039323166353330633239386264306337386361653430633838
|
35346664393165643239366436346233343566646438363533313964323831303566666264356337
|
||||||
66366636616661313939316562373330313564383033643035393738353939613066316138643238
|
66663638633064643962346136616333303064356331343031623863353365613661353333656362
|
||||||
35376336633238636463376234376364386464396461636336313562616361396435323639666433
|
37393062356661383430353365643964343462666436643236386164313932656234383039633537
|
||||||
34653139613962623235613035363634383735326564333332333632656237333238356566646536
|
30653833626331373930666239623639306433633038643963656634616337366230623265626539
|
||||||
62346435303932363231306634643037623935653235613330666666656433396463656231643364
|
66323638616330393135356134373735613933373735306330363437373237346532663239343636
|
||||||
34313235613064646432633935656231643162363530313761303339323830653564303963643532
|
37393937646365343065613233333331353763656535373739663263636233363230636166363530
|
||||||
39326163396461613161363031616336666564326630323465663831653431353566643661656435
|
38333065386138306165303664393064643836346264373939383535323365383363666436356639
|
||||||
35636238633663346139343732353233663930353664623636303134303633356232313063346566
|
32323364643937343139633435623734303839383566656539376263356634653838616337386466
|
||||||
30633762653239356131613539396435396235326431633062616436613266353266636133656531
|
66366632346331323039663863393666376637626137393037623161323931346565343935343863
|
||||||
63346533383764393733396436306136383830313265656539376136343536353737313365333865
|
38643864643739356331316162633233666162373430623337383734336564633463643338666637
|
||||||
61653665393037346231656663363432666332383837393264656231386435323333376633333265
|
35656265656461633537643739323833373838653130613831343336356331373737616465646564
|
||||||
39633563653161663531303330393237316132653339653531316538316534353334383161623833
|
64353734333262303038663631663231326636633532343164643338333237333331316165623032
|
||||||
63656534643833656366623031326132343732663536393636393537383338613462336638626334
|
34386137386534633432303638653366333962646532336130646139656136656533666533336233
|
||||||
39326264623032393661303335356235343736613964636261633038333236623232613633343263
|
62646261636630663161313966323862363761333135663864646339393835316437613862383434
|
||||||
34363865306233346433393664363038303464363834313463636363366333313433333930336634
|
63643436616432653662613531303361616263343365613437303838613332643637383439646664
|
||||||
65396232663031323965343336366339623239386566323362396564333932336134336231646430
|
32333761666237306232633832363362626239326139363363333530666630383736623839303065
|
||||||
34376236636536626264663532323530656634333137363431313339643164333236303337373639
|
33383562353733393830646661313632656361623037663262303665393532306335643465353436
|
||||||
31326131636161386665623838303939616337636666346363616465323263373061633832363839
|
63313834333732366530373366666335353630663633373333343434626664383137646538336666
|
||||||
39343131386333666231643931353330343136363732396465383336303866623733316235646234
|
33306666383838616435363037333062396461363634383236336130666635666539366462616238
|
||||||
65613531613333653231666234353532313738363266353336303564613061393639323933646339
|
31316265303961323666633065633961313963663962383837666565366361333836656364346137
|
||||||
64396334396431313563326136656539613535663334323330326566613264393965623065616634
|
65633030356432343935343139366138666137373734343361616132626630313833323461666265
|
||||||
32313333663535313531343363656230656334346430643365363838656430616366653766333136
|
61383565666138393937396265306634323939366334663635663566343932656633366333386434
|
||||||
32346137656136666432383934313865613535303962333464316465313464333233646162376165
|
38303530333034346139366432396663386631663931623761633961626539386234623837376262
|
||||||
37363265316139643332393761663164346537663064346133323661393030393533396633646134
|
38326235316330643635383934303030663634633834613164623332393365333966316131316161
|
||||||
39383539333364626263323364353764316539323162346434656234393562326133613632633137
|
35353965396337356463626661333232656236653930373531316163346465333862623734343438
|
||||||
34323537393838393534643861356365376461636235386638376661623439303832643231616431
|
65643837613962656162343866336634353436346337643761336531346164353765323238636262
|
||||||
32663264306166366336396130326435346432343732323764346232356439633361663937313233
|
35663432396165306464353266323532343363333232653865616563613030356236323036396266
|
||||||
62636130663238333433396335356331653166366130626632663162653736656238343134353134
|
64376162323436646532626363363933386433333033363864356334323839613134613935383764
|
||||||
39373663633437626661393734363264313137663138643665353633366663366562386337396561
|
30626435633531633361366332623861626363366531393861383134636230643032336663666131
|
||||||
38383464333531306138316266626461326531616364303732343337386464366464633834383439
|
37643630313138623433316562643435323762653438333335323566353264323033373834316631
|
||||||
66303334333234306166396235666164313833333164356561663063326563303934373933313334
|
66346332373366313234323237343931393437646130386261656565663065636132333035666164
|
||||||
32326466343761333666373936373332663939643662363665323534333638316637666665326564
|
35663762373131643164323031653365333339326264626234623537326638663432666235343730
|
||||||
63616134623530333739633265343637626561383831663836626538313539653536373165636133
|
61623961333439633265316431366434356161613166326162383732386166383036313838386539
|
||||||
62396432376332356133336461633664336264616566376664643861363838313766393833343366
|
64636664366130306365333762646133336465313033306563353633626561356336313966383931
|
||||||
31386636343835663062396232646663363935396366343361633462643734373437666331383035
|
32613863653662316136376330373335316437376233323930356434663732376631643963383938
|
||||||
30373963323834343138653063313635643062396130373861643134363062363135623730663335
|
61346262333339613736386333323534396130313935663632663432623162643738313238613438
|
||||||
34373935623239363866393932363966366233643732646461343964383563393064396331353331
|
34303163333731626664303337393965313237333936663664323565366434643436623539633139
|
||||||
31646662323364376639316562666465356438386637393130616330663563633839326661643239
|
62363431656634663636646465396238323165376131396635663764356532656534373065663461
|
||||||
62346633353963336239633738336431326638626232313965336361636430323739653734636436
|
34383765333933383561646430633235306533303134633939336561623265626431613833346161
|
||||||
39316363316137366233616431346639663335393737653562356532363634346237336266333132
|
63616662616239393566396332313430393563313063383836623331393965623065643535333734
|
||||||
31343836326538653164653163653738656238326366313532613433333337383263646439326661
|
63323431633533373632663939343830663530353533373730323939363931353438373338313466
|
||||||
65306135363138646665363463636436303864316432663734393130313932643833356161373139
|
64326461393564383961326463326335376238353034656531643732633461353862636466646264
|
||||||
65376334376136313237393336636630643933373165336432643233306366633663333930396364
|
64613635333334363237353235393539363766643838396330663437373639323432653165366339
|
||||||
31393739333730326434313639376365356432376338386430363133666436643837633533616333
|
30353739383739633564313635653763346631343934636437346362373363316339396437323733
|
||||||
36363464633233343130656163353137663165343064373039363439346631393436393430383361
|
62343733303834323736383834306232333932626166626536356338663862613339353531363935
|
||||||
61353563346531353561303935363531333235313731303237326334363763646131653961613334
|
38653761663066363265383139373536353638623330333239636361646564303039343930623638
|
||||||
33306534663238343433363237393234643236393931343230656438353866313638636633396464
|
30313864353833386263613633333335323932643462643133343461626365383238623639306631
|
||||||
61636561333562383964663261316135373235313234613564333333336438646636303561616634
|
32333538613432393662383434393831306236656236303234656235353637393137326665306661
|
||||||
63363033613238323463646165373361613834353230653138623132303731393436386139663533
|
38343961356631653631323261386630343263636537323434393736313333323334336639356263
|
||||||
38393263306139303231626363353931646163323364666161653861643739353262313561393165
|
34653237313930636237396264653336396132343364616339393061306435663632636433373065
|
||||||
6262
|
37383139363666393634323636386166666331346564333336386463626433376137646561353730
|
||||||
|
33633661616238623363366532336363386137333363346463303435353130643132313665643264
|
||||||
|
37613430633733353837626238303833343463363662303831303734336165383432663562613433
|
||||||
|
38613564643230326163333863633961323239376136323833326361653862643664666233306564
|
||||||
|
39653738343431616563333563666132323639366461343039363436613236646131343332363737
|
||||||
|
63633036646232646566623632383636303861646131373330623436333338346163316232363339
|
||||||
|
31346163623032353861343234333337623536386366643037393265316533356261313136313237
|
||||||
|
61663032363466626239336435303137636366626339623730653334313862306539633933336438
|
||||||
|
65663436623033336263383438353838353037363266636438346266363363633630386438396464
|
||||||
|
35346630336231393137366535333261313662663564653963316364653035613030323461643433
|
||||||
|
33623934666562646537623936666361386633393364343363323532306134623461366334393439
|
||||||
|
32643164306237393031663537636535396635623861383163343538633335383466643733653338
|
||||||
|
38306161643436346230383763313138393435356435336466303831613261356336366234366632
|
||||||
|
64323362373833336664323936323361616562653531373962396533623937386238333965333463
|
||||||
|
63366633373732643939306462356163366464333364613738393732326130303262626537323966
|
||||||
|
38313837643431393232633531663165373565343739363032336538363435613336616663613463
|
||||||
|
30333739366165613165636561373965356363346231646462626235636431623233663038373761
|
||||||
|
61363863316137393033306634343034666466346631393465646565646333343463363362363066
|
||||||
|
38366139386634313533323932666335336131393766666538386632336264303531306264336431
|
||||||
|
61303838616139376332613838376331336266316566613738643537393162623032346431666137
|
||||||
|
64666339393332376636646533636531303266633530633436326563396462313838616232353162
|
||||||
|
38363535396461326131323936336661656364663965313462326534323461313839313264333231
|
||||||
|
34633163626336316666386133336133306666353632333033353533376462616265356438373733
|
||||||
|
66666233333830393437333635326239373239303032633765303735646162386237306438646366
|
||||||
|
65333534666637653165653362613130626432373731656636396662616533333635303964373263
|
||||||
|
65646531633731323438636165303938356265383030653066393031383438303236323763623963
|
||||||
|
33383130616364383438663133646233623864376131323765623261353834633331353265303731
|
||||||
|
36306462396530356433356537393335323965663236646637306139363861353139626666333032
|
||||||
|
34306438383737656136313539623837663232306137333465613938353161356530646666643539
|
||||||
|
62333038306665383362393137613962323064653135376137626638613133363535646561353063
|
||||||
|
39386165333663336439386132303334306330373730666536373236333438636663626530663239
|
||||||
|
36663039616662636334663864323635636439616465623438393630383832353366323861613162
|
||||||
|
35333666313236653433343836623931333765613837343835363762663563363266303561623735
|
||||||
|
64353937623133306263393738303666323066353964373033383065316463383462326437653034
|
||||||
|
35663831653336663231636165633433663530313138373035313462393531653339303365646233
|
||||||
|
61303765396464653037306630623738306366383735386135316266356165376637396630643361
|
||||||
|
36656237663565303433313332386534356534653463313363626264313132373266383662343233
|
||||||
|
33326264636365303630653834646539653865663465326437623461363937653232386166373233
|
||||||
|
66353164383130633832666438336261666537623164363263306433633337666335656134353765
|
||||||
|
39373134623061653134636364643935373233396237386334653561313833343762323832313564
|
||||||
|
37356238656430623763396439383965323136323066346636313465633336393931373931633131
|
||||||
|
36363262336636316533396465613736663662306232323739363336666233386565373837326562
|
||||||
|
65643661626264303434613837623761333934633438326666386538303264643334383833616631
|
||||||
|
36646564383436346234303336666666313165396461373938316634323830383135343830666339
|
||||||
|
63303737613439633335376163616432623366333933643135363664626437636433323731663166
|
||||||
|
33303535643634633764643832633263376338313732376130336331653032663137613031333963
|
||||||
|
39643561383633383932653066363461663331383962373631636632356336396134653330373961
|
||||||
|
62643433363830306337663262383261386131626263303762663061353936623034316432613963
|
||||||
|
65333738326264313235303730303165386463353965613264383631666463326434656235323630
|
||||||
|
33656265313363306565626662303139353938306237346166663534353936633235383735656366
|
||||||
|
39646330656533353030353537636362316261353966373739636336633334633262343336623762
|
||||||
|
31383637376566616464316132346639626464366262343032363739336330616363373437346334
|
||||||
|
37326133633234373231346632613463383530323661386364376634336135363438376239663263
|
||||||
|
66363238643833333461626437356165346435386363356230346562376566386538633638376362
|
||||||
|
39313834633264613839396233653162313735313230346666393161643966626230383066623863
|
||||||
|
33613365323835343039336631336138656566306161643132333562373630383533613336373435
|
||||||
|
37383532356336303738343565326265336631393336666136626334313539383730653462373963
|
||||||
|
38346666663834333564646461356636336133316439303062643534303837633661303032393633
|
||||||
|
35636231333561343761626431373966623966346466633563626538336430646236613466303331
|
||||||
|
35363736366630363166396433653438643563326464636466633866353263633534313365353334
|
||||||
|
37383963363035303735666330323435623531303366663866643334366461313336303334616337
|
||||||
|
32343362336366623566356361646638633237306531396264643437356133653931396433383262
|
||||||
|
34303039353836373738623339393136386538643738326264323334623962323838636464663832
|
||||||
|
63656234636364386663333733663332393639613335666237653739316138383536366662393061
|
||||||
|
38393137383331386362386565303135656231336163363839323332613530336435623365393361
|
||||||
|
34343839373963666366633564343531326264323538393231373032663935343935396661313139
|
||||||
|
61626662636235653335653761666137313430353533383033363762396636366463363635386437
|
||||||
|
32383835653833643866633265666661363837396337616236306636333633616337336233353966
|
||||||
|
39613232653635373534373039636437393630303063623033366563366664633233323565363732
|
||||||
|
33336132653261643835336430613263323832333065663131343830316438306139653736326232
|
||||||
|
65313764386231623434643738383536323232373463393239323865313061366364656536626261
|
||||||
|
37353831366538653130356330303630313536336661353738303230336435333663393365656239
|
||||||
|
31386561636437303432613765353932306635366234383631346261646461346338366165633033
|
||||||
|
63363066363966373430376634633733323233313466303033663463323932376461366634323831
|
||||||
|
64656431316533613930376337323736633361386565376238336165323364316264666235316636
|
||||||
|
65666334363638336263626332346436366262626537356163356362666539616636623336343265
|
||||||
|
64616265333138333334636633613466656434333961316539326137656565346430646564313030
|
||||||
|
32653430303463613532313734666264336631333134626339613535346664306534343530343139
|
||||||
|
66663737343038313563623039633261393364343235656563663366383039393933353262323462
|
||||||
|
64376433386533353132313739393934306566613632613933343036633338353435353631643262
|
||||||
|
61356534373562333466366163333338303637623732373063646465656536313435333034666536
|
||||||
|
38303335376632616136363334356331313032333765626331663139643335383039333561663264
|
||||||
|
61353735306131656635333062613365343131383531393838376531626631396233613130646236
|
||||||
|
65396561633464626137313737323164646236303866366538616661323331653536613936353734
|
||||||
|
35616661383063313837376433343836353064643937386138626636373263326662346663343138
|
||||||
|
64363164646561613230323436373333623036316231643364366565313534383665666563306430
|
||||||
|
32383539633661376366316261333730316531376133376166646136623737626664656461303336
|
||||||
|
39653031636233646239626536306337623631353539373762663230393361313862633233633634
|
||||||
|
30663561313761613064376232613166663433316635623134386262386231386262613161333864
|
||||||
|
62626333343062363565663863383038363031333632336664323161383239306466643464623233
|
||||||
|
38623034623031343130613139383631656231343134373039333237343065313139313766326465
|
||||||
|
38383135306539363261386531363034653637663235353836343331376337356436393132633933
|
||||||
|
36313166643338353963616466623764363166663239356139346333373761653636386435663363
|
||||||
|
65303934393339353265613332366233373665376562383562663166303838363233393563353730
|
||||||
|
34663937313864346230306330323230666234373364666135306461363265373031343865313339
|
||||||
|
32356130613261323435656266323231633164376132353065336331663562666132396635653964
|
||||||
|
61343633323532653238396131373466393561386434356536383134623534303333333336303738
|
||||||
|
66353039643466353266366436663636363438383964353635663664316463373238326164333433
|
||||||
|
38623335653366623961303161316261653038373837643733363534343663393065316130663035
|
||||||
|
63623931383263316333333863623836623635353862396439623264613234306538633466366131
|
||||||
|
61373237323337656162303366336363386139613635616135323035343764333166346337353034
|
||||||
|
65626535623034343232333735326438303438646263303261326664656339633762326338336137
|
||||||
|
39653730393164316530633635306333613333623064336635373732313431306631383737326338
|
||||||
|
33303931626431643465316438666432613564616238343237383165366262303237613961383630
|
||||||
|
36643439626633306263316437653866343362623536303032343137366535356165313430393264
|
||||||
|
33316339323838663062623566646365663734663339653638636363363861313361326166663630
|
||||||
|
34633433326633613035663639386434663430626464623761623931353639306232386533363538
|
||||||
|
38666636613432303739313030353830343535636633353664666661643531356138613731363563
|
||||||
|
32616239343063386536383462633332303136343333306131616563326438653136313830303038
|
||||||
|
32613961366634303562653436626132643338336235383638653961303262383565626632376363
|
||||||
|
65613865663638653739356365383731333664363732643834356339623138613838343631303433
|
||||||
|
65326262373963646361306432303336376638383061303164643030393633333737363166366339
|
||||||
|
34616637363261376462356230376166373630313862643732616431303161653965373032336366
|
||||||
|
64656138336237386362643638316465373464353862666236336532343436633534363966333031
|
||||||
|
39623933306631633366366138303237366638623435323766383562626233396436616261663738
|
||||||
|
63363632323335336366343264396662383562366430323866653635663962393136373732646331
|
||||||
|
33333963373261613161623733626138613037653136643735323331653338373830343633303263
|
||||||
|
30356261323766333161633738376238336666353733383666626634313437326462383335616138
|
||||||
|
656664303532663862373935343637336266
|
||||||
@@ -0,0 +1,12 @@
|
|||||||
|
---
|
||||||
|
# Single-origin layout: one hostname, Caddy routes /health, /ws, /api/daemon/ws to the backend
|
||||||
|
multica_layout: single
|
||||||
|
multica_domain: multica.wdw-labs.cloud
|
||||||
|
|
||||||
|
# TLS: acme_http | cloudflare_dns | internal
|
||||||
|
caddy_tls_mode: cloudflare_dns
|
||||||
|
caddy_acme_email: "ryan.blundon@protonmail.com"
|
||||||
|
|
||||||
|
# Pin for reproducible deploys (git tag + matching image tag)
|
||||||
|
# multica_version: v0.4.5
|
||||||
|
# multica_image_tag: v0.4.5
|
||||||
@@ -0,0 +1,8 @@
|
|||||||
|
---
|
||||||
|
# Copy to vault.yml and encrypt: ansible-vault encrypt group_vars/multica/vault.yml
|
||||||
|
# Generate secrets with: openssl rand -hex 32 (postgres: openssl rand -hex 16)
|
||||||
|
vault_multica_jwt_secret: "CHANGEME"
|
||||||
|
vault_multica_postgres_password: "CHANGEME"
|
||||||
|
vault_multica_vcs_secret_key: "CHANGEME"
|
||||||
|
vault_cloudflare_api_token: "CHANGEME" # only for caddy_tls_mode: cloudflare_dns
|
||||||
|
# vault_multica_resend_api_key: "" # optional: email verification codes
|
||||||
@@ -2,11 +2,14 @@
|
|||||||
# ------------------------------------------------------------------------------
|
# ------------------------------------------------------------------------------
|
||||||
# FILE: ansible/host_vars/astro_orbiter/vars.yml
|
# FILE: ansible/host_vars/astro_orbiter/vars.yml
|
||||||
# HOST: astro-orbiter (10.1.71.130)
|
# HOST: astro-orbiter (10.1.71.130)
|
||||||
# ROLE: Ollama inference host with AMD RX 5700 GPU passthrough
|
# ROLE: llama.cpp LLM inference host — Ryzen 7 5800XT / RTX 3090 (ATX rebuild,
|
||||||
|
# 2026-08-04). Superseded the prior AMD RX 5700 / Ollama config below;
|
||||||
|
# drive was transplanted into new hardware, not reinstalled.
|
||||||
# ------------------------------------------------------------------------------
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
ansible_host: 10.1.71.130
|
ansible_host: 10.1.71.130
|
||||||
ansible_user: wed
|
ansible_user: jarvis
|
||||||
|
ansible_ssh_private_key_file: ~/.ssh/id_jarvis
|
||||||
ansible_become: true
|
ansible_become: true
|
||||||
|
|
||||||
# LVM root expansion — xlarge template uses sda3 partition, standard VG/LV names
|
# LVM root expansion — xlarge template uses sda3 partition, standard VG/LV names
|
||||||
@@ -15,11 +18,218 @@ common_root_pv: /dev/sda3
|
|||||||
common_root_vg: ubuntu-vg
|
common_root_vg: ubuntu-vg
|
||||||
common_root_lv: ubuntu-lv
|
common_root_lv: ubuntu-lv
|
||||||
|
|
||||||
# Ollama — all defaults apply; explicitly documented here for visibility
|
# --- Staged GGUF models for the llama.cpp router (:8002) ---------------------
|
||||||
ollama_rocm_version: "6.2"
|
# Data-driven list consumed by roles/llm-inference-multimodel tasks/models.yml
|
||||||
ollama_default_model: "qwen3:8b"
|
# (loop -> tasks/stage_model.yml). Each entry is idempotently staged into
|
||||||
ollama_hsa_override_gfx_version: "10.1.0"
|
# /opt/models: stat + EXACT-size check vs HF manifest; skip (no download, no
|
||||||
ollama_data_disk: /dev/sdb
|
# restart) when present + size matches. Source repos are public bartowski GGUFs
|
||||||
ollama_data_vg: ollama-vg
|
# on HuggingFace (no auth). A router restart is notified ONLY when a new GGUF
|
||||||
ollama_data_lv: ollama-lv
|
# is actually downloaded.
|
||||||
ollama_data_dir: /var/lib/ollama
|
# Added 2026-08-12 (War Machine): codify Phi-3.5-mini-instruct-Q8_0 and
|
||||||
|
# Meta-Llama-3.1-8B-Instruct-Q4_K_M as router models alongside the production
|
||||||
|
# Qwen3.6-35B-A3B-UD-Q4_K_S. The live files were already present/correct on
|
||||||
|
# astro-orbiter; this pass codifies them. Future adds = append to this list.
|
||||||
|
# Router --models-max override for astro-orbiter.
|
||||||
|
# Default in defaults/main.yml is 1 (conservative). Bumped to 4 on 2026-08-12
|
||||||
|
# (t_33acbb2e) so the router can keep more than one GGUF resident on-demand
|
||||||
|
# and LRU-evict when needed.
|
||||||
|
#
|
||||||
|
# VRAM NOTE (t_33acbb2e, updated t_55c164f5, updated t_34b96e83, updated t_f5f7e9ad, updated t_441470b9, updated t_c5cef2b2):
|
||||||
|
# With models-max=4 and all 6 GGUFs registered, worst case is all 6 loaded simultaneously:
|
||||||
|
# Qwen3.8-27B Q4_K_M: ~20.0GB (weights ~17.1GB + KV ~2.9GB @ 65536 ctx, q4_0) ← CORRECTED (ctx rolled back from 128K to 65536, t_c9fed26c 2026-08-18)
|
||||||
|
# Phi-3.5-mini-instruct Q8_0: ~4.3GB (weights ~3.8GB + KV ~0.5GB @ 32K ctx)
|
||||||
|
# Meta-Llama-3.1-8B Q4_K_M: ~5.6GB (weights ~4.6GB + KV ~0.2GB @ 8K ctx)
|
||||||
|
# Qwen2.5-Coder-14B Q4_K_M: ~9.0GB (weights ~8.4GB + KV ~0.6GB @ 16K ctx)
|
||||||
|
# nomic-embed-text-v1.5 Q4_K_M: ~0.09GB (~84MB, embedding only — no KV cache)
|
||||||
|
# Qwen3-8B Q4_K_M: ~5.5GB (weights ~4.68GB + KV ~0.5GB @ 32K ctx, q4_0)
|
||||||
|
# Total worst-case: ~44.5GB >> 24GB RTX 3090
|
||||||
|
#
|
||||||
|
# OOM RISK: Full co-residency is impossible on 24GB. LRU eviction prevents this
|
||||||
|
# in practice: models-max=4 means the router can REGISTER 6 models but only keeps
|
||||||
|
# up to 4 LOADED simultaneously — the router will evict the LRU model when a new
|
||||||
|
# one is needed. nomic-embed-text-v1.5 is pinned via sleep-idle-seconds=-1 and
|
||||||
|
# load-on-startup=true but it uses only ~84MB, so it never meaningfully changes
|
||||||
|
# the budget. In single-user homelab operation, only one generative model is active
|
||||||
|
# at a time alongside the always-resident embedding model.
|
||||||
|
# Qwen3.8-27B alone uses ~17,804 MiB (weights+KV @ 65536 ctx); co-residency
|
||||||
|
# with Coder (~9GB) = ~27GB > 24GB. LRU eviction handles this automatically.
|
||||||
|
# Ryan should be aware this means model-switching always incurs a ~30-60s
|
||||||
|
# cold-load latency when switching between Qwen3.8-27B and any other model.
|
||||||
|
# Proceeding to models-max=4 as instructed; flagged for Ryan's attention.
|
||||||
|
# Router --models-max override for astro-orbiter.
|
||||||
|
# UPDATED (t_f5f7e9ad, 2026-08-16): Set to 2 because Qwen3.8-27B-Q4_K_M
|
||||||
|
# uses 17,804 MiB at 65536 ctx. Only nomic-embed (558MB, pinned) and ONE
|
||||||
|
# generative model can be resident simultaneously. Co-residency of Qwen3.8
|
||||||
|
# with any auxiliary model (Phi 8.3GB, Llama 5.9GB, Coder 9GB) exceeds 24GB.
|
||||||
|
# models-max=2: slot 1 = nomic-embed (pinned, always loaded), slot 2 = LRU
|
||||||
|
# generative model (Qwen3.8 primary, cold-loaded on first request ~30-60s;
|
||||||
|
# auxiliary models evict it on demand, and vice versa).
|
||||||
|
# NOTE: Qwen3.8 does NOT have load-on-startup — it loads on first request.
|
||||||
|
# This avoids an LRU eviction race with nomic-embed at startup.
|
||||||
|
# UPDATED (t_72646029, 2026-08-17): CPU offload for Coder + Llama changes the
|
||||||
|
# constraint. Coder and Llama now use CPU inference (n-gpu-layers=0). GPU-resident
|
||||||
|
# VRAM: Qwen3.8 (~17,804 MiB at 65536 ctx) + nomic-embed (558 MiB, pinned) plus
|
||||||
|
# the CUDA-context buffers llama.cpp 6ea215d allocates for the CPU models (~1.4-1.7GB
|
||||||
|
# each) = ~20,004 MiB steady-state, below the 24,576 MiB physical limit.
|
||||||
|
# CORRECTED (t_c5cef2b2, 2026-08-19): ctx-size was rolled back from 131072 to 65536
|
||||||
|
# (t_c9fed26c 2026-08-18). Qwen3.8 VRAM at 65536: 17,804 MiB (not 20,302 MiB).
|
||||||
|
# models-max raised to 4: nomic (slot 1, pinned) + Qwen3.8 (slot 2, GPU) +
|
||||||
|
# Llama (slot 3, CPU) + Coder (slot 4, CPU). Phi (GPU, ~8.3GB) and new
|
||||||
|
# Qwen3-8B (GPU, ~5.5GB) can also be requested but evict Qwen3.8 due to VRAM.
|
||||||
|
# models-max=4 is required so CPU-offloaded models count as loaded without
|
||||||
|
# evicting Qwen3.8.
|
||||||
|
llm_router_models_max: 4
|
||||||
|
|
||||||
|
llm_staged_models:
|
||||||
|
- filename: "Phi-3.5-mini-instruct-Q8_0.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Phi-3.5-mini-instruct-GGUF/resolve/main/Phi-3.5-mini-instruct-Q8_0.gguf"
|
||||||
|
size_bytes: 4061222688
|
||||||
|
source_repo: "bartowski/Phi-3.5-mini-instruct-GGUF"
|
||||||
|
- filename: "Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
|
||||||
|
size_bytes: 4920739232
|
||||||
|
source_repo: "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF"
|
||||||
|
- filename: "Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf"
|
||||||
|
size_bytes: 8988111072
|
||||||
|
source_repo: "bartowski/Qwen2.5-Coder-14B-Instruct-GGUF"
|
||||||
|
- filename: "nomic-embed-text-v1.5-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.Q4_K_M.gguf"
|
||||||
|
size_bytes: 84106624
|
||||||
|
source_repo: "nomic-ai/nomic-embed-text-v1.5-GGUF"
|
||||||
|
# Added t_c5cef2b2 (2026-08-19, War Machine): Qwen3-8B dense 8B model for
|
||||||
|
# aux tasks (routing, rewriting, structured extraction, tool-call construction).
|
||||||
|
# Source: bartowski/Qwen_Qwen3-8B-GGUF (public, no auth). HF filename is
|
||||||
|
# Qwen_Qwen3-8B-Q4_K_M.gguf; stored locally as Qwen3-8B-Q4_K_M.gguf.
|
||||||
|
# Exact size verified from HF manifest (content-length): 5,027,784,224 bytes.
|
||||||
|
# VRAM: ~4.68GB weights + ~0.5GB KV @ 32K ctx (q4_0) ≈ 5.2GB total.
|
||||||
|
# Thinking mode ON by default; use /no_think for latency-sensitive aux tasks.
|
||||||
|
- filename: "Qwen3-8B-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Qwen_Qwen3-8B-GGUF/resolve/main/Qwen_Qwen3-8B-Q4_K_M.gguf"
|
||||||
|
size_bytes: 5027784224
|
||||||
|
source_repo: "bartowski/Qwen_Qwen3-8B-GGUF"
|
||||||
|
|
||||||
|
# --- deploy-vllm role: vllm_models override (t_r1d32b_swap, 2026-09-01) -----
|
||||||
|
# Ansible's hash_behaviour is "replace" (see ansible.cfg) — a host_vars list
|
||||||
|
# variable REPLACES the role default list wholesale, it does not deep-merge.
|
||||||
|
#
|
||||||
|
# SWAP (Ryan direction, 2026-09-01): Qwen2.5-32B-Instruct-AWQ retired,
|
||||||
|
# replaced with DeepSeek-R1-Distill-Qwen-32B-AWQ, max_model_len=32768.
|
||||||
|
# "Single model only" — nomic-embed-text-v1.5 (embedding, :8020) and
|
||||||
|
# Qwen3-8B-AWQ (aux, :8010, already disabled) are BOTH disabled here.
|
||||||
|
# DeepSeek gets the full 24GB card to itself. Nothing in production
|
||||||
|
# consumed nomic-embed at the time of this swap (Hindsight uses its own
|
||||||
|
# bundled 384-dim embedder; OpenViking pointed at the old llama-swap
|
||||||
|
# endpoint, already stopped) — confirmed with Ryan before disabling.
|
||||||
|
#
|
||||||
|
# Model choice: casperhansen/deepseek-r1-distill-qwen-32b-awq — same
|
||||||
|
# quantizer/toolchain (AutoAWQ) as the outgoing Qwen2.5-32B-Instruct-AWQ,
|
||||||
|
# widely used, 4-bit GEMM AWQ, ~19.3GB on disk (4 safetensors shards).
|
||||||
|
# Architecture: Qwen2ForCausalLM (DeepSeek-R1 distilled onto Qwen2.5-32B
|
||||||
|
# base) — same vLLM code path as the outgoing model, no new serving
|
||||||
|
# support needed. Native max_position_embeddings=131072; we cap at 32768
|
||||||
|
# per the task's explicit max-model-len requirement.
|
||||||
|
#
|
||||||
|
# VRAM math: ~19.3GB weights (4-bit AWQ) + KV cache at 32768 ctx (GQA,
|
||||||
|
# 8 KV heads, 128 head_dim, 64 layers, fp16 KV by default) ≈ 19.3GB +
|
||||||
|
# ~4GB KV+overhead ≈ 23.3GB — tight but the FULL 24GB card is now
|
||||||
|
# available (no co-resident nomic-embed/Qwen3-8B taking a share, unlike
|
||||||
|
# the outgoing Qwen2.5-32B config). gpu_memory_utilization=0.95 (role
|
||||||
|
# default) + enforce_eager retained as the proven-stable mitigation from
|
||||||
|
# t_e6facb19/t_ca1af9fb (avoids CUDA graph capture VRAM spike; this host's
|
||||||
|
# only validated way to avoid crash-loop-to-stabilize behavior on this
|
||||||
|
# card). If 0.95 OOMs at 32768 ctx once tested live, drop to 0.90 next
|
||||||
|
# (documented fallback, same pattern as the outgoing model).
|
||||||
|
#
|
||||||
|
# DeepSeek-R1 output note: reasoning traces stream in <think> tags before
|
||||||
|
# the final answer — this is expected R1-distill behavior, not a bug.
|
||||||
|
# Model card recommends temperature 0.5-0.7 (not 0, not vLLM's greedy
|
||||||
|
# default) to avoid repetition/incoherence; not set here (server-side
|
||||||
|
# default), left to be set client-side per the model card's guidance —
|
||||||
|
# flagging for whoever wires this into Hermes profile configs next.
|
||||||
|
vllm_models:
|
||||||
|
- id: "Gemma-4-26B-A4B-it-AWQ"
|
||||||
|
hf_repo: "cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit"
|
||||||
|
role: primary
|
||||||
|
# NO quantization field set (unlike the AutoAWQ-quantized DeepSeek/
|
||||||
|
# Qwen2.5 models above) — live test (2026-09-01) found this repo's
|
||||||
|
# config.json declares quant_method: "compressed-tensors" (llm-compressor
|
||||||
|
# tool output, not classic AutoAWQ), even though the repo name says
|
||||||
|
# "AWQ-4bit". Passing --quantization awq explicitly caused a hard
|
||||||
|
# pydantic ValidationError at every single startup attempt: "Quantization
|
||||||
|
# method specified in the model config (compressed-tensors) does not
|
||||||
|
# match the quantization method specified in the `quantization` argument
|
||||||
|
# (awq)." vLLM auto-detects the quant method correctly from the model's
|
||||||
|
# own config.json when --quantization is omitted — confirmed fix, clean
|
||||||
|
# start. Lesson: don't trust a HF repo's naming convention ("...-AWQ...")
|
||||||
|
# for the `quantization:` field here — check config.json's quant_method.
|
||||||
|
port: 8000
|
||||||
|
# Ryan direction (2026-09-01, t_gemma4_swap): DeepSeek-R1-Distill-Qwen-32B
|
||||||
|
# retired after confirming its `auto` tool-choice reliability is a known,
|
||||||
|
# documented DeepSeek-R1-distillation limitation (trained on pure
|
||||||
|
# reasoning traces, no function-calling data — GitHub-confirmed upstream,
|
||||||
|
# not a vLLM config gap). Replaced with Gemma 4 26B A4B (Google,
|
||||||
|
# Apache 2.0, US-origin — matches Ryan's standing model-origin
|
||||||
|
# preference, unlike Qwen/DeepSeek). Chose MoE (26B A4B, 3.8B active)
|
||||||
|
# over the dense 31B variant: ~3.7GB smaller on-disk AWQ footprint
|
||||||
|
# (17.2GB vs 20.9GB) buys more KV-cache headroom on this tight 24GB
|
||||||
|
# card, and decode should be faster (memory-bandwidth-bound on active
|
||||||
|
# params, not total params). Tradeoff accepted: MoE scores lower than
|
||||||
|
# dense on the Tau2 tool-use benchmark (68.2% vs 76.9%) but still beats
|
||||||
|
# every other size in the family except the 31B on most reasoning
|
||||||
|
# benchmarks. Model choice: cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit —
|
||||||
|
# AutoAWQ 4-bit group_size=32, MoE expert layers (gate/up/down/router)
|
||||||
|
# explicitly excluded from quantization ("ignore" list in config.json)
|
||||||
|
# per standard llm-compressor MoE quant practice — only the dense
|
||||||
|
# attention/projection layers are 4-bit, experts stay higher precision.
|
||||||
|
# Native architecture: Gemma4ForConditionalGeneration (registered
|
||||||
|
# natively in this host's installed vLLM 0.28.0 — vllm/model_executor/
|
||||||
|
# models/registry.py line 415 — no plugin/trust-remote-code needed).
|
||||||
|
# Native max_position_embeddings: 262144 (256K) — Hermes's 64K floor is
|
||||||
|
# comfortably covered without any context-extension trick.
|
||||||
|
max_model_len: 65536
|
||||||
|
# VRAM math (not yet live-validated — see swap validation log below
|
||||||
|
# once run): AWQ weights ~17.2GB on disk (dense attn 4-bit + MoE
|
||||||
|
# experts higher-precision, per config.json's compressed-tensors
|
||||||
|
# ignore list). Starting the KV cache dtype at int4_per_token_head
|
||||||
|
# from the outset (rather than fp16 -> fp8 -> int4 trial-and-error like
|
||||||
|
# the DeepSeek swap) since that same escalation pattern is expected to
|
||||||
|
# repeat on this VRAM-constrained card for any 20+ GB model at >32K ctx.
|
||||||
|
kv_cache_dtype: int4_per_token_head
|
||||||
|
gpu_memory_utilization: 0.95
|
||||||
|
enforce_eager: true
|
||||||
|
# Native tool-calling + reasoning support (no `hermes` workaround
|
||||||
|
# needed, unlike DeepSeek-R1-Distill): Gemma4EngineToolParser and
|
||||||
|
# Gemma4ParserReasoningAdapter are both registered natively in this
|
||||||
|
# host's vLLM 0.28.0 (vllm/tool_parsers/__init__.py,
|
||||||
|
# vllm/reasoning/__init__.py) — purpose-built for this model's actual
|
||||||
|
# output format, not a same-family approximation.
|
||||||
|
enable_auto_tool_choice: true
|
||||||
|
tool_call_parser: gemma4
|
||||||
|
reasoning_parser: gemma4
|
||||||
|
enabled: true
|
||||||
|
- id: "Qwen3-8B-AWQ"
|
||||||
|
hf_repo: "Qwen/Qwen3-8B-AWQ"
|
||||||
|
role: aux
|
||||||
|
quantization: awq
|
||||||
|
port: 8010
|
||||||
|
max_model_len: 32768
|
||||||
|
gpu_memory_utilization: 0.15
|
||||||
|
enforce_eager: true
|
||||||
|
enabled: false # single-model deployment — see swap note above
|
||||||
|
- id: "nomic-embed-text-v1.5"
|
||||||
|
hf_repo: "nomic-ai/nomic-embed-text-v1.5"
|
||||||
|
role: embedding
|
||||||
|
quantization: none
|
||||||
|
port: 8020
|
||||||
|
max_model_len: 2048
|
||||||
|
gpu_memory_utilization: 0.05
|
||||||
|
trust_remote_code: true
|
||||||
|
enabled: false # single-model deployment — see swap note above
|
||||||
|
|
||||||
|
# --- deploy-vllm role: boot persistence (unchanged) -------------------------
|
||||||
|
# Still permanent/boot-persistent — same policy as the outgoing Qwen2.5-32B
|
||||||
|
# deployment (t_5508360a), just now serving one model instead of two.
|
||||||
|
vllm_service_enabled: true
|
||||||
|
vllm_service_state: started
|
||||||
|
|
||||||
@@ -0,0 +1,16 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: ansible/host_vars/astro_orbiter/vars.yml
|
||||||
|
# HOST: astro-orbiter (10.1.71.130)
|
||||||
|
# ROLE: Ollama inference host with AMD RX 5700 GPU passthrough
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
ansible_host: 10.1.71.131
|
||||||
|
ansible_user: wed
|
||||||
|
ansible_become: true
|
||||||
|
|
||||||
|
# LVM root expansion — xlarge template uses sda3 partition, standard VG/LV names
|
||||||
|
common_expand_root_lvm: true
|
||||||
|
common_root_pv: /dev/sda3
|
||||||
|
common_root_vg: ubuntu-vg
|
||||||
|
common_root_lv: ubuntu-lv
|
||||||
@@ -0,0 +1,26 @@
|
|||||||
|
---
|
||||||
|
# Paperclip Docker deployment
|
||||||
|
paperclip_domain: cranium-command.wdw-labs.cloud
|
||||||
|
paperclip_base_path: /opt/paperclip
|
||||||
|
paperclip_port: 3100
|
||||||
|
certbot_email: ryan.blundon@protonmail.com
|
||||||
|
|
||||||
|
# vLLM inference endpoint (local)
|
||||||
|
vllm_endpoint: "http://127.0.0.1:8000"
|
||||||
|
|
||||||
|
hermes_model:
|
||||||
|
provider: custom
|
||||||
|
default: Gemma-4-26B-A4B-Hermes-VLM-MLX # from http://fantasmic.wdw-labs.cloud:8000/v1/models
|
||||||
|
base_url: http://fantasmic.wdw-labs.cloud:8000/v1
|
||||||
|
api_key: "{{ vault_fantasmic_api_key }}"
|
||||||
|
|
||||||
|
# # DNS entries (if using your existing dns-manager role)
|
||||||
|
# dns_entries:
|
||||||
|
# - name: illuminations
|
||||||
|
# domain: wdw-labs.cloud
|
||||||
|
# type: A
|
||||||
|
# value: "{{ ansible_host }}"
|
||||||
|
# - name: muppet-vision
|
||||||
|
# domain: wdw-labs.cloud
|
||||||
|
# type: A
|
||||||
|
# value: "{{ ansible_host }}"
|
||||||
@@ -0,0 +1,244 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: ansible/host_vars/illuminations/vars.yml
|
||||||
|
# HOST: illuminations (10.1.71.130)
|
||||||
|
# ROLE: llama.cpp LLM inference host — Ryzen 7 5800XT / RTX 3090 (ATX rebuild,
|
||||||
|
# 2026-08-04). Superseded the prior AMD RX 5700 / Ollama config below;
|
||||||
|
# drive was transplanted into new hardware, not reinstalled.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
ansible_host: 10.1.71.130
|
||||||
|
ansible_user: jarvis
|
||||||
|
ansible_ssh_private_key_file: ~/.ssh/id_jarvis
|
||||||
|
ansible_become: true
|
||||||
|
|
||||||
|
# LVM root expansion — xlarge template uses sda3 partition, standard VG/LV names
|
||||||
|
common_expand_root_lvm: true
|
||||||
|
common_root_pv: /dev/sda3
|
||||||
|
common_root_vg: ubuntu-vg
|
||||||
|
common_root_lv: ubuntu-lv
|
||||||
|
|
||||||
|
# --- Staged GGUF models for the llama.cpp router (:8002) ---------------------
|
||||||
|
# Data-driven list consumed by roles/llm-inference-multimodel tasks/models.yml
|
||||||
|
# (loop -> tasks/stage_model.yml). Each entry is idempotently staged into
|
||||||
|
# /opt/models: stat + EXACT-size check vs HF manifest; skip (no download, no
|
||||||
|
# restart) when present + size matches. Source repos are public bartowski GGUFs
|
||||||
|
# on HuggingFace (no auth). A router restart is notified ONLY when a new GGUF
|
||||||
|
# is actually downloaded.
|
||||||
|
# Added 2026-08-12 (War Machine): codify Phi-3.5-mini-instruct-Q8_0 and
|
||||||
|
# Meta-Llama-3.1-8B-Instruct-Q4_K_M as router models alongside the production
|
||||||
|
# Qwen3.6-35B-A3B-UD-Q4_K_S. The live files were already present/correct on
|
||||||
|
# astro-orbiter; this pass codifies them. Future adds = append to this list.
|
||||||
|
# Router --models-max override for astro-orbiter.
|
||||||
|
# Default in defaults/main.yml is 1 (conservative). Bumped to 4 on 2026-08-12
|
||||||
|
# (t_33acbb2e) so the router can keep more than one GGUF resident on-demand
|
||||||
|
# and LRU-evict when needed.
|
||||||
|
#
|
||||||
|
# VRAM NOTE (t_33acbb2e, updated t_55c164f5, updated t_34b96e83, updated t_f5f7e9ad, updated t_441470b9, updated t_c5cef2b2):
|
||||||
|
# With models-max=4 and all 6 GGUFs registered, worst case is all 6 loaded simultaneously:
|
||||||
|
# Qwen3.8-27B Q4_K_M: ~20.0GB (weights ~17.1GB + KV ~2.9GB @ 65536 ctx, q4_0) ← CORRECTED (ctx rolled back from 128K to 65536, t_c9fed26c 2026-08-18)
|
||||||
|
# Phi-3.5-mini-instruct Q8_0: ~4.3GB (weights ~3.8GB + KV ~0.5GB @ 32K ctx)
|
||||||
|
# Meta-Llama-3.1-8B Q4_K_M: ~5.6GB (weights ~4.6GB + KV ~0.2GB @ 8K ctx)
|
||||||
|
# Qwen2.5-Coder-14B Q4_K_M: ~9.0GB (weights ~8.4GB + KV ~0.6GB @ 16K ctx)
|
||||||
|
# nomic-embed-text-v1.5 Q4_K_M: ~0.09GB (~84MB, embedding only — no KV cache)
|
||||||
|
# Qwen3-8B Q4_K_M: ~5.5GB (weights ~4.68GB + KV ~0.5GB @ 32K ctx, q4_0)
|
||||||
|
# Total worst-case: ~44.5GB >> 24GB RTX 3090
|
||||||
|
#
|
||||||
|
# OOM RISK: Full co-residency is impossible on 24GB. LRU eviction prevents this
|
||||||
|
# in practice: models-max=4 means the router can REGISTER 6 models but only keeps
|
||||||
|
# up to 4 LOADED simultaneously — the router will evict the LRU model when a new
|
||||||
|
# one is needed. nomic-embed-text-v1.5 is pinned via sleep-idle-seconds=-1 and
|
||||||
|
# load-on-startup=true but it uses only ~84MB, so it never meaningfully changes
|
||||||
|
# the budget. In single-user homelab operation, only one generative model is active
|
||||||
|
# at a time alongside the always-resident embedding model.
|
||||||
|
# Qwen3.8-27B alone uses ~17,804 MiB (weights+KV @ 65536 ctx); co-residency
|
||||||
|
# with Coder (~9GB) = ~27GB > 24GB. LRU eviction handles this automatically.
|
||||||
|
# Ryan should be aware this means model-switching always incurs a ~30-60s
|
||||||
|
# cold-load latency when switching between Qwen3.8-27B and any other model.
|
||||||
|
# Proceeding to models-max=4 as instructed; flagged for Ryan's attention.
|
||||||
|
# Router --models-max override for astro-orbiter.
|
||||||
|
# UPDATED (t_f5f7e9ad, 2026-08-16): Set to 2 because Qwen3.8-27B-Q4_K_M
|
||||||
|
# uses 17,804 MiB at 65536 ctx. Only nomic-embed (558MB, pinned) and ONE
|
||||||
|
# generative model can be resident simultaneously. Co-residency of Qwen3.8
|
||||||
|
# with any auxiliary model (Phi 8.3GB, Llama 5.9GB, Coder 9GB) exceeds 24GB.
|
||||||
|
# models-max=2: slot 1 = nomic-embed (pinned, always loaded), slot 2 = LRU
|
||||||
|
# generative model (Qwen3.8 primary, cold-loaded on first request ~30-60s;
|
||||||
|
# auxiliary models evict it on demand, and vice versa).
|
||||||
|
# NOTE: Qwen3.8 does NOT have load-on-startup — it loads on first request.
|
||||||
|
# This avoids an LRU eviction race with nomic-embed at startup.
|
||||||
|
# UPDATED (t_72646029, 2026-08-17): CPU offload for Coder + Llama changes the
|
||||||
|
# constraint. Coder and Llama now use CPU inference (n-gpu-layers=0). GPU-resident
|
||||||
|
# VRAM: Qwen3.8 (~17,804 MiB at 65536 ctx) + nomic-embed (558 MiB, pinned) plus
|
||||||
|
# the CUDA-context buffers llama.cpp 6ea215d allocates for the CPU models (~1.4-1.7GB
|
||||||
|
# each) = ~20,004 MiB steady-state, below the 24,576 MiB physical limit.
|
||||||
|
# CORRECTED (t_c5cef2b2, 2026-08-19): ctx-size was rolled back from 131072 to 65536
|
||||||
|
# (t_c9fed26c 2026-08-18). Qwen3.8 VRAM at 65536: 17,804 MiB (not 20,302 MiB).
|
||||||
|
# models-max raised to 4: nomic (slot 1, pinned) + Qwen3.8 (slot 2, GPU) +
|
||||||
|
# Llama (slot 3, CPU) + Coder (slot 4, CPU). Phi (GPU, ~8.3GB) and new
|
||||||
|
# Qwen3-8B (GPU, ~5.5GB) can also be requested but evict Qwen3.8 due to VRAM.
|
||||||
|
# models-max=4 is required so CPU-offloaded models count as loaded without
|
||||||
|
# evicting Qwen3.8.
|
||||||
|
llm_router_models_max: 4
|
||||||
|
|
||||||
|
llm_staged_models:
|
||||||
|
- filename: "Phi-3.5-mini-instruct-Q8_0.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Phi-3.5-mini-instruct-GGUF/resolve/main/Phi-3.5-mini-instruct-Q8_0.gguf"
|
||||||
|
size_bytes: 4061222688
|
||||||
|
source_repo: "bartowski/Phi-3.5-mini-instruct-GGUF"
|
||||||
|
- filename: "Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
|
||||||
|
size_bytes: 4920739232
|
||||||
|
source_repo: "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF"
|
||||||
|
- filename: "Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf"
|
||||||
|
size_bytes: 8988111072
|
||||||
|
source_repo: "bartowski/Qwen2.5-Coder-14B-Instruct-GGUF"
|
||||||
|
- filename: "nomic-embed-text-v1.5-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.Q4_K_M.gguf"
|
||||||
|
size_bytes: 84106624
|
||||||
|
source_repo: "nomic-ai/nomic-embed-text-v1.5-GGUF"
|
||||||
|
# Added t_c5cef2b2 (2026-08-19, War Machine): Qwen3-8B dense 8B model for
|
||||||
|
# aux tasks (routing, rewriting, structured extraction, tool-call construction).
|
||||||
|
# Source: bartowski/Qwen_Qwen3-8B-GGUF (public, no auth). HF filename is
|
||||||
|
# Qwen_Qwen3-8B-Q4_K_M.gguf; stored locally as Qwen3-8B-Q4_K_M.gguf.
|
||||||
|
# Exact size verified from HF manifest (content-length): 5,027,784,224 bytes.
|
||||||
|
# VRAM: ~4.68GB weights + ~0.5GB KV @ 32K ctx (q4_0) ≈ 5.2GB total.
|
||||||
|
# Thinking mode ON by default; use /no_think for latency-sensitive aux tasks.
|
||||||
|
- filename: "Qwen3-8B-Q4_K_M.gguf"
|
||||||
|
url: "https://huggingface.co/bartowski/Qwen_Qwen3-8B-GGUF/resolve/main/Qwen_Qwen3-8B-Q4_K_M.gguf"
|
||||||
|
size_bytes: 5027784224
|
||||||
|
source_repo: "bartowski/Qwen_Qwen3-8B-GGUF"
|
||||||
|
|
||||||
|
# --- deploy-vllm role: vllm_models override (t_r1d32b_swap, 2026-09-01) -----
|
||||||
|
# Ansible's hash_behaviour is "replace" (see ansible.cfg) — a host_vars list
|
||||||
|
# variable REPLACES the role default list wholesale, it does not deep-merge.
|
||||||
|
#
|
||||||
|
# SWAP (Ryan direction, 2026-09-01): Qwen2.5-32B-Instruct-AWQ retired,
|
||||||
|
# replaced with DeepSeek-R1-Distill-Qwen-32B-AWQ, max_model_len=32768.
|
||||||
|
# "Single model only" — nomic-embed-text-v1.5 (embedding, :8020) and
|
||||||
|
# Qwen3-8B-AWQ (aux, :8010, already disabled) are BOTH disabled here.
|
||||||
|
# DeepSeek gets the full 24GB card to itself. Nothing in production
|
||||||
|
# consumed nomic-embed at the time of this swap (Hindsight uses its own
|
||||||
|
# bundled 384-dim embedder; OpenViking pointed at the old llama-swap
|
||||||
|
# endpoint, already stopped) — confirmed with Ryan before disabling.
|
||||||
|
#
|
||||||
|
# Model choice: casperhansen/deepseek-r1-distill-qwen-32b-awq — same
|
||||||
|
# quantizer/toolchain (AutoAWQ) as the outgoing Qwen2.5-32B-Instruct-AWQ,
|
||||||
|
# widely used, 4-bit GEMM AWQ, ~19.3GB on disk (4 safetensors shards).
|
||||||
|
# Architecture: Qwen2ForCausalLM (DeepSeek-R1 distilled onto Qwen2.5-32B
|
||||||
|
# base) — same vLLM code path as the outgoing model, no new serving
|
||||||
|
# support needed. Native max_position_embeddings=131072; we cap at 32768
|
||||||
|
# per the task's explicit max-model-len requirement.
|
||||||
|
#
|
||||||
|
# VRAM math: ~19.3GB weights (4-bit AWQ) + KV cache at 32768 ctx (GQA,
|
||||||
|
# 8 KV heads, 128 head_dim, 64 layers, fp16 KV by default) ≈ 19.3GB +
|
||||||
|
# ~4GB KV+overhead ≈ 23.3GB — tight but the FULL 24GB card is now
|
||||||
|
# available (no co-resident nomic-embed/Qwen3-8B taking a share, unlike
|
||||||
|
# the outgoing Qwen2.5-32B config). gpu_memory_utilization=0.95 (role
|
||||||
|
# default) + enforce_eager retained as the proven-stable mitigation from
|
||||||
|
# t_e6facb19/t_ca1af9fb (avoids CUDA graph capture VRAM spike; this host's
|
||||||
|
# only validated way to avoid crash-loop-to-stabilize behavior on this
|
||||||
|
# card). If 0.95 OOMs at 32768 ctx once tested live, drop to 0.90 next
|
||||||
|
# (documented fallback, same pattern as the outgoing model).
|
||||||
|
#
|
||||||
|
# DeepSeek-R1 output note: reasoning traces stream in <think> tags before
|
||||||
|
# the final answer — this is expected R1-distill behavior, not a bug.
|
||||||
|
# Model card recommends temperature 0.5-0.7 (not 0, not vLLM's greedy
|
||||||
|
# default) to avoid repetition/incoherence; not set here (server-side
|
||||||
|
# default), left to be set client-side per the model card's guidance —
|
||||||
|
# flagging for whoever wires this into Hermes profile configs next.
|
||||||
|
vllm_models:
|
||||||
|
- id: "Gemma-4-26B-A4B-it-AWQ"
|
||||||
|
hf_repo: "cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit"
|
||||||
|
role: primary
|
||||||
|
# NO quantization field set (unlike the AutoAWQ-quantized DeepSeek/
|
||||||
|
# Qwen2.5 models above) — live test (2026-09-01) found this repo's
|
||||||
|
# config.json declares quant_method: "compressed-tensors" (llm-compressor
|
||||||
|
# tool output, not classic AutoAWQ), even though the repo name says
|
||||||
|
# "AWQ-4bit". Passing --quantization awq explicitly caused a hard
|
||||||
|
# pydantic ValidationError at every single startup attempt: "Quantization
|
||||||
|
# method specified in the model config (compressed-tensors) does not
|
||||||
|
# match the quantization method specified in the `quantization` argument
|
||||||
|
# (awq)." vLLM auto-detects the quant method correctly from the model's
|
||||||
|
# own config.json when --quantization is omitted — confirmed fix, clean
|
||||||
|
# start. Lesson: don't trust a HF repo's naming convention ("...-AWQ...")
|
||||||
|
# for the `quantization:` field here — check config.json's quant_method.
|
||||||
|
port: 8000
|
||||||
|
# Ryan direction (2026-09-01, t_gemma4_swap): DeepSeek-R1-Distill-Qwen-32B
|
||||||
|
# retired after confirming its `auto` tool-choice reliability is a known,
|
||||||
|
# documented DeepSeek-R1-distillation limitation (trained on pure
|
||||||
|
# reasoning traces, no function-calling data — GitHub-confirmed upstream,
|
||||||
|
# not a vLLM config gap). Replaced with Gemma 4 26B A4B (Google,
|
||||||
|
# Apache 2.0, US-origin — matches Ryan's standing model-origin
|
||||||
|
# preference, unlike Qwen/DeepSeek). Chose MoE (26B A4B, 3.8B active)
|
||||||
|
# over the dense 31B variant: ~3.7GB smaller on-disk AWQ footprint
|
||||||
|
# (17.2GB vs 20.9GB) buys more KV-cache headroom on this tight 24GB
|
||||||
|
# card, and decode should be faster (memory-bandwidth-bound on active
|
||||||
|
# params, not total params). Tradeoff accepted: MoE scores lower than
|
||||||
|
# dense on the Tau2 tool-use benchmark (68.2% vs 76.9%) but still beats
|
||||||
|
# every other size in the family except the 31B on most reasoning
|
||||||
|
# benchmarks. Model choice: cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit —
|
||||||
|
# AutoAWQ 4-bit group_size=32, MoE expert layers (gate/up/down/router)
|
||||||
|
# explicitly excluded from quantization ("ignore" list in config.json)
|
||||||
|
# per standard llm-compressor MoE quant practice — only the dense
|
||||||
|
# attention/projection layers are 4-bit, experts stay higher precision.
|
||||||
|
# Native architecture: Gemma4ForConditionalGeneration (registered
|
||||||
|
# natively in this host's installed vLLM 0.28.0 — vllm/model_executor/
|
||||||
|
# models/registry.py line 415 — no plugin/trust-remote-code needed).
|
||||||
|
# Native max_position_embeddings: 262144 (256K) — Hermes's 64K floor is
|
||||||
|
# comfortably covered without any context-extension trick.
|
||||||
|
max_model_len: 65536
|
||||||
|
# VRAM math (not yet live-validated — see swap validation log below
|
||||||
|
# once run): AWQ weights ~17.2GB on disk (dense attn 4-bit + MoE
|
||||||
|
# experts higher-precision, per config.json's compressed-tensors
|
||||||
|
# ignore list). Starting the KV cache dtype at int4_per_token_head
|
||||||
|
# from the outset (rather than fp16 -> fp8 -> int4 trial-and-error like
|
||||||
|
# the DeepSeek swap) since that same escalation pattern is expected to
|
||||||
|
# repeat on this VRAM-constrained card for any 20+ GB model at >32K ctx.
|
||||||
|
kv_cache_dtype: int4_per_token_head
|
||||||
|
gpu_memory_utilization: 0.95
|
||||||
|
enforce_eager: true
|
||||||
|
# Native tool-calling + reasoning support (no `hermes` workaround
|
||||||
|
# needed, unlike DeepSeek-R1-Distill): Gemma4EngineToolParser and
|
||||||
|
# Gemma4ParserReasoningAdapter are both registered natively in this
|
||||||
|
# host's vLLM 0.28.0 (vllm/tool_parsers/__init__.py,
|
||||||
|
# vllm/reasoning/__init__.py) — purpose-built for this model's actual
|
||||||
|
# output format, not a same-family approximation.
|
||||||
|
enable_auto_tool_choice: true
|
||||||
|
tool_call_parser: gemma4
|
||||||
|
reasoning_parser: gemma4
|
||||||
|
enabled: true
|
||||||
|
- id: "Qwen3-8B-AWQ"
|
||||||
|
hf_repo: "Qwen/Qwen3-8B-AWQ"
|
||||||
|
role: aux
|
||||||
|
quantization: awq
|
||||||
|
port: 8010
|
||||||
|
max_model_len: 32768
|
||||||
|
gpu_memory_utilization: 0.15
|
||||||
|
enforce_eager: true
|
||||||
|
enabled: false # single-model deployment — see swap note above
|
||||||
|
- id: "nomic-embed-text-v1.5"
|
||||||
|
hf_repo: "nomic-ai/nomic-embed-text-v1.5"
|
||||||
|
role: embedding
|
||||||
|
quantization: none
|
||||||
|
port: 8020
|
||||||
|
max_model_len: 2048
|
||||||
|
gpu_memory_utilization: 0.05
|
||||||
|
trust_remote_code: true
|
||||||
|
enabled: false # single-model deployment — see swap note above
|
||||||
|
|
||||||
|
# --- deploy-vllm role: boot persistence (unchanged) -------------------------
|
||||||
|
# Still permanent/boot-persistent — same policy as the outgoing Qwen2.5-32B
|
||||||
|
# deployment (t_5508360a), just now serving one model instead of two.
|
||||||
|
vllm_service_enabled: true
|
||||||
|
vllm_service_state: started
|
||||||
|
|
||||||
|
# Paperclip Docker deployment
|
||||||
|
nginx_proxy_certbot_email: ryan.blundon@protonmail.com
|
||||||
|
# nginx_proxy_certbot_staging: true # remove after first successful real issuance
|
||||||
|
|
||||||
|
hermes_model:
|
||||||
|
provider: custom
|
||||||
|
default: Gemma-4-26B-A4B-Hermes-VLM-MLX # from http://fantasmic.wdw-labs.cloud:8000/v1/models
|
||||||
|
base_url: http://fantasmic.wdw-labs.cloud:8000/v1
|
||||||
|
api_key: "{{ vault_fantasmic_api_key }}"
|
||||||
@@ -0,0 +1,16 @@
|
|||||||
|
---
|
||||||
|
# Host-specific vars for main-street-station (JMRI headless server)
|
||||||
|
# LCRR - Lake Country Railroad, Milwaukee Road Oct 1956, HO scale
|
||||||
|
|
||||||
|
# JMRI profile ID — find with: ls ~/.jmri/profiles/ on the old box
|
||||||
|
# Format: <name>.<8-char-hex> e.g. LCRR.3d3f1dfc
|
||||||
|
# TODO: fill in after restoring config from GitHub backup
|
||||||
|
jmri_profile_id: ""
|
||||||
|
|
||||||
|
# USB serial device for NCE command station
|
||||||
|
# Verify after install: ls -la /dev/ttyUSB* /dev/ttyACM*
|
||||||
|
jmri_serial_device: /dev/ttyUSB0
|
||||||
|
|
||||||
|
# Path to JMRI config backup for restore task (leave empty to skip)
|
||||||
|
# Point at a local checkout of the LCRR GitHub repo
|
||||||
|
jmri_config_src: ""
|
||||||
@@ -0,0 +1,10 @@
|
|||||||
|
---
|
||||||
|
# main-street-station — JMRI / LCRR server
|
||||||
|
jmri_profile_id: "Lake_Country_Railroad.3e8b1d4b"
|
||||||
|
jmri_lcrr_repo: "ssh://git@gitea.mk-labs.cloud:2221/rblundon/LCRR.git"
|
||||||
|
jmri_lcrr_branch: "clean-profile"
|
||||||
|
jmri_leviton_email: "{{ leviton_email }}"
|
||||||
|
jmri_leviton_password: "{{ leviton_password }}"
|
||||||
|
jmri_ssh_authorized_key: "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINnSM/9fO8rz/amqkyoGUzUKNNzzmtSXPwOCr1O9zKNO ansible"
|
||||||
|
jmri_ssh_authorized_keys_extra:
|
||||||
|
- "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIG6HaK4Y21UwPRbAZ986L7I9QnUdyq53114+9kO8X4bL rblundon@laptop"
|
||||||
+57
-2
@@ -50,21 +50,72 @@ nextcloud_server:
|
|||||||
|
|
||||||
semaphore_server:
|
semaphore_server:
|
||||||
hosts:
|
hosts:
|
||||||
imagineering:
|
figment:
|
||||||
ansible_host: 10.1.71.37
|
ansible_host: 10.1.71.37
|
||||||
|
ansible_user: wed
|
||||||
ansible_become: true
|
ansible_become: true
|
||||||
|
|
||||||
n8n_server:
|
n8n_server:
|
||||||
hosts:
|
hosts:
|
||||||
tiki-room:
|
tiki-room:
|
||||||
|
|
||||||
ollama_server:
|
astro_orbiter:
|
||||||
hosts:
|
hosts:
|
||||||
astro-orbiter:
|
astro-orbiter:
|
||||||
|
|
||||||
|
claude_servers:
|
||||||
|
hosts:
|
||||||
|
haunted-mansion:
|
||||||
|
ansible_host: 10.1.71.137
|
||||||
|
ansible_user: wed
|
||||||
|
ansible_become: true
|
||||||
|
ansible_ssh_private_key_file: ~/.ssh/ansible
|
||||||
|
|
||||||
|
hermes_server:
|
||||||
|
hosts:
|
||||||
|
carousel-of-progress:
|
||||||
|
ansible_host: 10.1.71.131
|
||||||
|
ansible_user: wed
|
||||||
|
ansible_become: true
|
||||||
|
ansible_ssh_private_key_file: ~/.ssh/ansible
|
||||||
|
|
||||||
|
honcho_server:
|
||||||
|
hosts:
|
||||||
|
lincoln:
|
||||||
|
ansible_host: 10.1.71.132
|
||||||
|
ansible_user: wed
|
||||||
|
ansible_become: true
|
||||||
|
|
||||||
|
paperclip_server:
|
||||||
|
hosts:
|
||||||
|
illuminations:
|
||||||
ansible_host: 10.1.71.130
|
ansible_host: 10.1.71.130
|
||||||
ansible_user: wed
|
ansible_user: wed
|
||||||
ansible_become: true
|
ansible_become: true
|
||||||
|
|
||||||
|
multica_agent_hosts:
|
||||||
|
hosts:
|
||||||
|
haunted-mansion:
|
||||||
|
ansible_host: haunted-mansion.wdw-labs.cloud
|
||||||
|
multica_device_name: haunted-mansion
|
||||||
|
spaceship-earth:
|
||||||
|
ansible_host: spaceship-earth.wdw-labs.cloud
|
||||||
|
multica_device_name: spaceship-earth
|
||||||
|
|
||||||
|
multica:
|
||||||
|
hosts:
|
||||||
|
muppet-vision:
|
||||||
|
ansible_host: 10.1.71.136
|
||||||
|
ansible_user: wed
|
||||||
|
ansible_become: true
|
||||||
|
|
||||||
|
jmri_server:
|
||||||
|
hosts:
|
||||||
|
main-street-station:
|
||||||
|
ansible_host: 192.168.10.40
|
||||||
|
ansible_user: wed
|
||||||
|
ansible_become: true
|
||||||
|
|
||||||
papermc_server:
|
papermc_server:
|
||||||
# ansible-galaxy role install engonzal.papermc
|
# ansible-galaxy role install engonzal.papermc
|
||||||
hosts:
|
hosts:
|
||||||
@@ -73,6 +124,10 @@ papermc_server:
|
|||||||
dev_servers:
|
dev_servers:
|
||||||
hosts:
|
hosts:
|
||||||
scrim:
|
scrim:
|
||||||
|
backstage:
|
||||||
|
ansible_host: 10.1.71.133
|
||||||
|
ansible_user: wed
|
||||||
|
ansible_become: true
|
||||||
|
|
||||||
# dhcp_server:
|
# dhcp_server:
|
||||||
# hosts:
|
# hosts:
|
||||||
|
|||||||
@@ -6,7 +6,8 @@
|
|||||||
#
|
#
|
||||||
# 1. Syncs boilerplates/traefik/dynamic/ to lightning-lane
|
# 1. Syncs boilerplates/traefik/dynamic/ to lightning-lane
|
||||||
# 2. Scans the directory for service configs
|
# 2. Scans the directory for service configs
|
||||||
# 3. Creates CNAME records for each service -> lightning-lane
|
# 3. Extracts all hostnames from Host() rules (supports multi-host)
|
||||||
|
# 4. Creates CNAME records for each hostname -> lightning-lane
|
||||||
#
|
#
|
||||||
# PREREQUISITES:
|
# PREREQUISITES:
|
||||||
# - Service dynamic config YAML committed to boilerplates/traefik/dynamic/
|
# - Service dynamic config YAML committed to boilerplates/traefik/dynamic/
|
||||||
@@ -14,15 +15,6 @@
|
|||||||
#
|
#
|
||||||
# USAGE:
|
# USAGE:
|
||||||
# ansible-playbook -i inventory.yml playbooks/add_service_route.yml
|
# ansible-playbook -i inventory.yml playbooks/add_service_route.yml
|
||||||
#
|
|
||||||
# ADDING A NEW SERVICE:
|
|
||||||
# 1. Create boilerplates/traefik/dynamic/<service>.yml
|
|
||||||
# 2. Commit and push
|
|
||||||
# 3. Run this playbook
|
|
||||||
#
|
|
||||||
# EXCLUDING FILES:
|
|
||||||
# Files that are not service routes (e.g., default.yml for middleware
|
|
||||||
# definitions) should be added to the exclude_configs list below.
|
|
||||||
# ------------------------------------------------------------------------------
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
- name: Sync Traefik routes and ensure DNS records
|
- name: Sync Traefik routes and ensure DNS records
|
||||||
@@ -33,13 +25,12 @@
|
|||||||
vars:
|
vars:
|
||||||
base_domain: "local.mk-labs.cloud"
|
base_domain: "local.mk-labs.cloud"
|
||||||
dns_server: "monorail"
|
dns_server: "monorail"
|
||||||
traefik_host: "10.1.71.35"
|
traefik_host: "lightning-lane.local.mk-labs.cloud"
|
||||||
traefik_user: "wed"
|
traefik_user: "wed"
|
||||||
traefik_dynamic_path: "/opt/docker/traefik/dynamic/"
|
traefik_dynamic_path: "/opt/docker/traefik/dynamic/"
|
||||||
dynamic_config_dir: "{{ playbook_dir }}/../../boilerplates/traefik/dynamic"
|
dynamic_config_dir: "{{ playbook_dir }}/../../boilerplates/traefik/dynamic"
|
||||||
|
|
||||||
# Files in the dynamic directory that are NOT service routes
|
# Files in the dynamic directory that are NOT service routes
|
||||||
# (middleware definitions, TLS options, etc.)
|
|
||||||
exclude_configs:
|
exclude_configs:
|
||||||
- default.yml
|
- default.yml
|
||||||
|
|
||||||
@@ -53,38 +44,52 @@
|
|||||||
register: sync_result
|
register: sync_result
|
||||||
changed_when: "'sending incremental file list' in sync_result.stdout"
|
changed_when: "'sending incremental file list' in sync_result.stdout"
|
||||||
|
|
||||||
# ── Step 2: Discover service configs ──
|
# ── Step 2: Discover hostnames from Traefik router rules ──
|
||||||
- name: Find all dynamic config files
|
- name: Find all dynamic config files
|
||||||
ansible.builtin.find:
|
ansible.builtin.find:
|
||||||
paths: "{{ dynamic_config_dir }}"
|
paths: "{{ dynamic_config_dir }}"
|
||||||
patterns: "*.yml"
|
patterns: "*.yml"
|
||||||
register: config_files
|
register: config_files
|
||||||
|
|
||||||
- name: Build service list from config filenames
|
- name: Read config files
|
||||||
ansible.builtin.set_fact:
|
ansible.builtin.slurp:
|
||||||
service_names: >-
|
src: "{{ item.path }}"
|
||||||
{{ config_files.files
|
register: slurped_configs
|
||||||
| map(attribute='path')
|
loop: "{{ config_files.files }}"
|
||||||
| map('basename')
|
when: item.path | basename not in exclude_configs
|
||||||
| reject('in', exclude_configs)
|
|
||||||
| map('regex_replace', '\.yml$', '')
|
|
||||||
| list }}
|
|
||||||
|
|
||||||
- name: Display services to route
|
- name: Extract all hostnames from Host() rules
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
hostnames: >-
|
||||||
|
{% set hosts = [] -%}
|
||||||
|
{% for result in slurped_configs.results if result.content is defined -%}
|
||||||
|
{% set content = result.content | b64decode -%}
|
||||||
|
{% for match in content | regex_findall('Host\(`([^`]+)`\)') -%}
|
||||||
|
{% for h in match.split(' || ') -%}
|
||||||
|
{% set h = h | regex_replace('`', '') | trim -%}
|
||||||
|
{% if h.endswith('.local.mk-labs.cloud') and h not in hosts -%}
|
||||||
|
{% set _ = hosts.append(h) -%}
|
||||||
|
{% endif -%}
|
||||||
|
{% endfor -%}
|
||||||
|
{% endfor -%}
|
||||||
|
{% endfor -%}
|
||||||
|
{{ hosts | unique | list }}
|
||||||
|
|
||||||
|
- name: Display hostnames to create
|
||||||
ansible.builtin.debug:
|
ansible.builtin.debug:
|
||||||
msg: "Services found: {{ service_names }}"
|
msg: "Hostnames found: {{ hostnames }}"
|
||||||
|
|
||||||
# ── Step 3: Create DNS CNAME records ──
|
# ── Step 3: Create DNS CNAME records ──
|
||||||
- name: Create DNS CNAME record for each service
|
- name: Create DNS CNAME record for each hostname
|
||||||
effectivelywild.technitium_dns.technitium_dns_add_record:
|
effectivelywild.technitium_dns.technitium_dns_add_record:
|
||||||
api_url: "http://{{ dns_server }}.{{ base_domain }}"
|
api_url: "http://{{ dns_server }}.{{ base_domain }}"
|
||||||
api_token: "{{ vault_technitium_api_key }}"
|
api_token: "{{ vault_technitium_api_key }}"
|
||||||
zone: "{{ base_domain }}"
|
zone: "{{ base_domain }}"
|
||||||
name: "{{ item }}.{{ base_domain }}"
|
name: "{{ item }}"
|
||||||
type: "CNAME"
|
type: "CNAME"
|
||||||
cname: "lightning-lane.{{ base_domain }}"
|
cname: "lightning-lane.{{ base_domain }}"
|
||||||
ttl: 360
|
ttl: 360
|
||||||
validate_certs: false
|
validate_certs: false
|
||||||
loop: "{{ service_names }}"
|
loop: "{{ hostnames }}"
|
||||||
loop_control:
|
loop_control:
|
||||||
label: "{{ item }}.{{ base_domain }}"
|
label: "{{ item }}"
|
||||||
@@ -0,0 +1,40 @@
|
|||||||
|
---
|
||||||
|
- name: Build Paperclip Docker image from source
|
||||||
|
hosts: illuminations
|
||||||
|
become: true
|
||||||
|
vars:
|
||||||
|
paperclip_repo_dir: /opt/paperclip-repo
|
||||||
|
paperclip_image_name: paperclip-local
|
||||||
|
paperclip_image_tag: latest
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
- name: Install git (if not present)
|
||||||
|
apt:
|
||||||
|
name: git
|
||||||
|
state: present
|
||||||
|
|
||||||
|
- name: Clone or update Paperclip repository
|
||||||
|
git:
|
||||||
|
repo: https://github.com/paperclipai/paperclip.git
|
||||||
|
dest: "{{ paperclip_repo_dir }}"
|
||||||
|
update: yes
|
||||||
|
register: git_clone
|
||||||
|
|
||||||
|
- name: Build Paperclip Docker image
|
||||||
|
shell: |
|
||||||
|
cd {{ paperclip_repo_dir }}
|
||||||
|
docker build --target production -t {{ paperclip_image_name }}:{{ paperclip_image_tag }} .
|
||||||
|
register: docker_build
|
||||||
|
changed_when: "'Successfully tagged' in docker_build.stdout"
|
||||||
|
|
||||||
|
- name: Show build result
|
||||||
|
debug:
|
||||||
|
msg: "Built image: {{ paperclip_image_name }}:{{ paperclip_image_tag }}"
|
||||||
|
|
||||||
|
- name: Show image details
|
||||||
|
shell: docker images {{ paperclip_image_name }}:{{ paperclip_image_tag }}
|
||||||
|
register: image_info
|
||||||
|
|
||||||
|
- name: Image info
|
||||||
|
debug:
|
||||||
|
msg: "{{ image_info.stdout_lines }}"
|
||||||
@@ -1,6 +1,6 @@
|
|||||||
---
|
---
|
||||||
- name: Apply common role
|
- name: Apply day0 baseline
|
||||||
hosts: "{{ target | default('all') }}"
|
hosts: "{{ target | default('all') }}"
|
||||||
become: true
|
become: true
|
||||||
roles:
|
roles:
|
||||||
- common
|
- day0-baseline
|
||||||
@@ -0,0 +1,32 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# day0_expand_root_lv.yml
|
||||||
|
# ----------------------------------------------------------------------------
|
||||||
|
# Reclaims unallocated PE on the root volume group, extending the root LV
|
||||||
|
# to fill the VG and resizing the underlying filesystem (ext4 or xfs).
|
||||||
|
#
|
||||||
|
# Belongs to the day0 host-provisioning lifecycle. The Ubuntu Server
|
||||||
|
# autoinstall template ships with the root LV at ~half the disk size by
|
||||||
|
# default; this playbook is the canonical one-shot fix-up for that.
|
||||||
|
#
|
||||||
|
# Idempotent and safe to re-run. Hosts without LVM are no-op'd cleanly.
|
||||||
|
#
|
||||||
|
# Opt-out: set `expand_root_lv_skip: true` in host_vars/<host>.yml for
|
||||||
|
# hosts where free PE should NOT be claimed by root (e.g. hosts with a
|
||||||
|
# planned second LV in the same VG for application data).
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# ansible-playbook playbooks/day0_expand_root_lv.yml
|
||||||
|
# ansible-playbook playbooks/day0_expand_root_lv.yml -e target=lincoln
|
||||||
|
# ansible-playbook playbooks/day0_expand_root_lv.yml -e target=honcho_server
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
- name: Expand root logical volume to fill VG
|
||||||
|
hosts: "{{ target | default('all') }}"
|
||||||
|
become: true
|
||||||
|
gather_facts: true
|
||||||
|
tasks:
|
||||||
|
- name: Apply expand_root_lv role unless host opts out
|
||||||
|
ansible.builtin.include_role:
|
||||||
|
name: expand_root_lv
|
||||||
|
when: not (expand_root_lv_skip | default(false) | bool)
|
||||||
@@ -0,0 +1,23 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# day0_linux_baseline.yml
|
||||||
|
# ----------------------------------------------------------------------------
|
||||||
|
# Applies the mk-labs Linux baseline (linux-baseline role) to one or more
|
||||||
|
# hosts. Idempotent and safe to re-run.
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# ansible-playbook playbooks/day0_linux_baseline.yml
|
||||||
|
# ansible-playbook playbooks/day0_linux_baseline.yml -e target=figment
|
||||||
|
# ansible-playbook playbooks/day0_linux_baseline.yml -e target=semaphore_server
|
||||||
|
#
|
||||||
|
# To trigger an opt-in full system upgrade:
|
||||||
|
# ansible-playbook playbooks/day0_linux_baseline.yml \
|
||||||
|
# -e target=figment -e 'baseline_features={"full_upgrade": true}'
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
- name: Apply mk-labs Linux baseline
|
||||||
|
hosts: "{{ target | default('all') }}"
|
||||||
|
become: true
|
||||||
|
gather_facts: true
|
||||||
|
roles:
|
||||||
|
- linux-baseline
|
||||||
@@ -0,0 +1,30 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# day0_provision.yml
|
||||||
|
# ----------------------------------------------------------------------------
|
||||||
|
# Umbrella day0 playbook. Runs the full host-provisioning lifecycle in
|
||||||
|
# the correct order against newly-built VMs, so the operator runs ONE
|
||||||
|
# command per new host rather than chaining day0 steps manually.
|
||||||
|
#
|
||||||
|
# Order matters:
|
||||||
|
# 1. linux-baseline — timezone, NTP, packages, SSH hardening, jarvis user
|
||||||
|
# 2. expand_root_lv — reclaim PE left unallocated by the Ubuntu
|
||||||
|
# autoinstall template default
|
||||||
|
#
|
||||||
|
# Idempotent: every step is safe to re-run. Suitable to apply periodically
|
||||||
|
# from Semaphore as a baseline-drift check.
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# ansible-playbook playbooks/day0_provision.yml -e target=lincoln
|
||||||
|
# ansible-playbook playbooks/day0_provision.yml -e target=honcho_server
|
||||||
|
#
|
||||||
|
# For finer control over a single phase, the constituent playbooks are:
|
||||||
|
# playbooks/day0_linux_baseline.yml
|
||||||
|
# playbooks/day0_expand_root_lv.yml
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
- name: Import day0 linux baseline
|
||||||
|
ansible.builtin.import_playbook: day0_linux_baseline.yml
|
||||||
|
|
||||||
|
- name: Import day0 expand root LV
|
||||||
|
ansible.builtin.import_playbook: day0_expand_root_lv.yml
|
||||||
@@ -0,0 +1,79 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# day1_deploy_hermes.yml
|
||||||
|
# Deploy Hermes Agent (Nous Research) on carousel-of-progress (10.1.71.131)
|
||||||
|
#
|
||||||
|
# FIRST-RUN WORKFLOW:
|
||||||
|
# 1. Run this playbook:
|
||||||
|
# ansible-playbook playbooks/day1_deploy_hermes.yml
|
||||||
|
#
|
||||||
|
# 2. SSH to the host and run the setup wizard as the hermes user:
|
||||||
|
# ssh wed@carousel-of-progress.local.mk-labs.cloud
|
||||||
|
# sudo -u hermes hermes setup
|
||||||
|
#
|
||||||
|
# 3. Once configured, start and verify the service:
|
||||||
|
# sudo systemctl start hermes
|
||||||
|
# sudo systemctl status hermes
|
||||||
|
# sudo journalctl -u hermes -f
|
||||||
|
#
|
||||||
|
# VARIABLES:
|
||||||
|
# hermes_skip_browser: true — set to skip Playwright/Chromium install
|
||||||
|
# (saves ~300MB if browser automation not needed)
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: Deploy Hermes Agent on carousel-of-progress
|
||||||
|
hosts: carousel-of-progress
|
||||||
|
gather_facts: true
|
||||||
|
|
||||||
|
pre_tasks:
|
||||||
|
- name: Verify target is carousel-of-progress
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- inventory_hostname == "carousel-of-progress"
|
||||||
|
fail_msg: >
|
||||||
|
This playbook is scoped to carousel-of-progress only.
|
||||||
|
Got: {{ inventory_hostname }}
|
||||||
|
|
||||||
|
- name: Confirm OS is Ubuntu
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ansible_distribution == "Ubuntu"
|
||||||
|
fail_msg: >
|
||||||
|
This playbook requires Ubuntu. Found: {{ ansible_distribution }}.
|
||||||
|
(If running Fedora, swap apt tasks for dnf and adjust Playwright deps.)
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: hermes
|
||||||
|
vars:
|
||||||
|
hermes_skip_browser: false # set true to skip Chromium install
|
||||||
|
|
||||||
|
post_tasks:
|
||||||
|
- name: Verify hermes binary is accessible system-wide
|
||||||
|
ansible.builtin.command: hermes --version
|
||||||
|
register: hermes_version_check
|
||||||
|
changed_when: false
|
||||||
|
failed_when: hermes_version_check.rc != 0
|
||||||
|
|
||||||
|
- name: Print hermes version
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "{{ hermes_version_check.stdout }}"
|
||||||
|
|
||||||
|
- name: Print post-install instructions
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "============================================================"
|
||||||
|
- "Hermes installed on carousel-of-progress (10.1.71.131)"
|
||||||
|
- "============================================================"
|
||||||
|
- "Next steps:"
|
||||||
|
- " 1. SSH to the host:"
|
||||||
|
- " ssh wed@carousel-of-progress.local.mk-labs.cloud"
|
||||||
|
- " 2. Run the setup wizard as the hermes user:"
|
||||||
|
- " sudo -u hermes hermes setup"
|
||||||
|
- " 3. After config, start the service:"
|
||||||
|
- " sudo systemctl start hermes"
|
||||||
|
- " 4. Verify:"
|
||||||
|
- " sudo systemctl status hermes"
|
||||||
|
- " sudo journalctl -u hermes -f"
|
||||||
|
- "============================================================"
|
||||||
|
- "Service is ENABLED but NOT STARTED — config required first."
|
||||||
|
- "============================================================"
|
||||||
@@ -0,0 +1,7 @@
|
|||||||
|
---
|
||||||
|
# Run after day1_deploy_nginx_proxy.yml (the role publishes its vhost through it).
|
||||||
|
- name: Deploy Hermes Agent (Docker)
|
||||||
|
hosts: illuminations
|
||||||
|
become: true
|
||||||
|
roles:
|
||||||
|
- hermes_docker
|
||||||
@@ -0,0 +1,18 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# day1_deploy_honcho.yml
|
||||||
|
# ----------------------------------------------------------------------------
|
||||||
|
# Deploys Honcho + pgvector PostgreSQL on the `lincoln` host. Assumes day0
|
||||||
|
# host provisioning (linux-baseline + expand_root_lv) is already complete.
|
||||||
|
#
|
||||||
|
# Run via:
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day0_provision.yml -e target=lincoln
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_honcho.yml
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
- name: Deploy Honcho on lincoln
|
||||||
|
hosts: honcho_server
|
||||||
|
become: true
|
||||||
|
gather_facts: true
|
||||||
|
roles:
|
||||||
|
- honcho
|
||||||
@@ -0,0 +1,24 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# day1_deploy_jmri.yml
|
||||||
|
# ----------------------------------------------------------------------------
|
||||||
|
# Deploys JMRI JmriFaceless headless server on main-street-station.
|
||||||
|
# Applies linux-baseline first, then the jmri role.
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# ansible-playbook playbooks/day1_deploy_jmri.yml
|
||||||
|
# ansible-playbook playbooks/day1_deploy_jmri.yml -e target=main-street-station
|
||||||
|
#
|
||||||
|
# Prerequisites:
|
||||||
|
# 1. Host is in inventory under jmri_server group
|
||||||
|
# 2. jmri_profile_id is set in host_vars/main-street-station.yml
|
||||||
|
# 3. SSH access as 'wed' with sudo
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
- name: Deploy JMRI headless server
|
||||||
|
hosts: "{{ target | default('jmri_server') }}"
|
||||||
|
become: true
|
||||||
|
gather_facts: true
|
||||||
|
roles:
|
||||||
|
- linux-baseline
|
||||||
|
- jmri
|
||||||
@@ -0,0 +1,25 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day1_deploy_llm_inference.yml
|
||||||
|
# DESCRIPTION: Day 1 playbook for astro-orbiter LLM inference stack.
|
||||||
|
# Deploys vLLM + Gemma 2 27B on RTX 3090 via OCuLink.
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# cd ~/git/homelab/ansible
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference.yml
|
||||||
|
#
|
||||||
|
# Phases (added incrementally — safe to re-run):
|
||||||
|
# 1. Foundation — groups, directories, vault assertion
|
||||||
|
# 2. Driver — nvidia-driver-595-open (idempotent; already installed)
|
||||||
|
# 3. vLLM — Python venv + pip install vllm
|
||||||
|
# 4. Model — HF login, Gemma 2 27B snapshot_download
|
||||||
|
# 5. Serve — systemd vllm-serve.service, health check
|
||||||
|
# 6. Integration — Hermes provider config on carousel
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Deploy LLM inference stack on astro-orbiter
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference
|
||||||
@@ -0,0 +1,35 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day1_deploy_llm_inference_multimodel.yml
|
||||||
|
# DESCRIPTION: Day 1 playbook for the dual-model (aux + tool-calling) rollout
|
||||||
|
# on astro-orbiter. Builds on roles/llm-inference (CUDA/driver
|
||||||
|
# already done) — does not replace it.
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# cd ~/git/homelab/ansible
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference_multimodel.yml
|
||||||
|
# # or scope to specific phases:
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference_multimodel.yml --tags discover
|
||||||
|
#
|
||||||
|
# EXECUTION CHANNEL (2026-08-12, War Machine): run via the Semaphore template
|
||||||
|
# "llm_inference_multimodel_stage_models" (scoped to --tags models). Do NOT
|
||||||
|
# run this via direct ansible-playbook or ad-hoc ssh/curl/systemctl — all
|
||||||
|
# homelab inference changes go through Ansible roles executed by Semaphore for
|
||||||
|
# audit/visibility. Phase 1 (models) is idempotent: it only downloads/stages a
|
||||||
|
# GGUF when missing or size-mismatched, and only restarts the router when a new
|
||||||
|
# GGUF is detected (normal re-runs that find the files correct touch nothing).
|
||||||
|
#
|
||||||
|
# Phases (see roles/llm-inference-multimodel/README.md for detail):
|
||||||
|
# 0. discover — read-only; confirm existing Gemma service management
|
||||||
|
# 1. models — idempotent GGUF downloads (Phi-4-14B, Mistral-Small-24B)
|
||||||
|
# 2. systemd — deploy both unit files, do NOT auto-start
|
||||||
|
# 3. firewall — scope ports 8000/8001, non-0.0.0.0 bind
|
||||||
|
# 4. verify — start both services, smoke test, VRAM check
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Deploy dual-model LLM inference stack on astro-orbiter
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference-multimodel
|
||||||
@@ -0,0 +1,106 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day1_deploy_llm_router_shadow.yml
|
||||||
|
# DESCRIPTION: Deploy llama-server in router mode on a shadow port (8003).
|
||||||
|
#
|
||||||
|
# This playbook deploys and validates the llama.cpp router mode supervisor on
|
||||||
|
# astro-orbiter (10.1.71.130) WITHOUT touching the production endpoint
|
||||||
|
# (llama-server-qwen, port 8002). All 7 dependent Hermes profiles
|
||||||
|
# (bruce-banner, groot, happy, heimdall, rocket-raccoon, war-machine, wong)
|
||||||
|
# remain pointing at port 8002 throughout this run.
|
||||||
|
#
|
||||||
|
# Usage (from ~/git/homelab/ansible):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_router_shadow.yml
|
||||||
|
#
|
||||||
|
# Tag-scoped runs (if you need to re-run one phase):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_router_shadow.yml \
|
||||||
|
# --tags router_systemd,router_firewall,router_verify
|
||||||
|
#
|
||||||
|
# Execution path (Ryan-approved 2026-08-12, task t_0cca74a2):
|
||||||
|
# Direct ansible-playbook as documented exception — Semaphore template for
|
||||||
|
# this role does not exist yet. Create template after cutover is confirmed.
|
||||||
|
# This is the same exception pattern used in prior sessions on this box.
|
||||||
|
#
|
||||||
|
# Pre-requisites:
|
||||||
|
# 1. llama-server binary at /opt/llama.cpp/build/bin/llama-server supports
|
||||||
|
# router mode (confirmed 2026-08-12: --models-dir flag present in --help).
|
||||||
|
# 2. /opt/models/ contains ONLY Qwen3.6-35B-A3B-UD-Q4_K_S.gguf
|
||||||
|
# (confirmed 2026-08-12: directory is clean, Phi-4/Mistral already deleted).
|
||||||
|
# 3. Port 8002 is in use by the production llama-server-qwen service —
|
||||||
|
# this playbook does NOT touch it.
|
||||||
|
#
|
||||||
|
# Validation gates this playbook runs (all hard gates EXCEPT Gate 4):
|
||||||
|
# Gate 1: /v1/models reports Qwen with n_ctx >= 64000 (64K Hermes floor)
|
||||||
|
# Gate 2: Tool-calling probe through router returns finish_reason=tool_calls
|
||||||
|
# Gate 2b: Hallucination stress test does NOT trigger spurious tool_calls
|
||||||
|
# Gate 3: nvidia-smi VRAM <= 23,000 MiB (--models-max 1 confirmed effective)
|
||||||
|
# Gate 4: Bundled SvelteKit UI check (nice-to-have, non-blocking)
|
||||||
|
#
|
||||||
|
# What happens after this playbook:
|
||||||
|
# War Machine posts validation gate results to Ryan.
|
||||||
|
# Ryan reviews and signs off on cutover (or requests changes).
|
||||||
|
# War Machine then runs day2_cutover_qwen_to_router.yml (not yet created)
|
||||||
|
# to promote the router to port 8002 and retire the bare llama-server-qwen.
|
||||||
|
#
|
||||||
|
# Reference: proposal at
|
||||||
|
# ~/friday/system/inbox/agents/war-machine/2026-08-12-qwen-router-mode-proposal.md
|
||||||
|
# Task: t_0cca74a2
|
||||||
|
# Author: War Machine (2026-08-12)
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Deploy llama-server router (shadow, port 8003) on astro-orbiter
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: true
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# Enable the router phase — this is the ONLY var that makes router.yml run.
|
||||||
|
# Default in defaults/main.yml is false (no-op). Flip here for the shadow run.
|
||||||
|
llm_router_enabled: true
|
||||||
|
|
||||||
|
# Qwen model ID as it appears in /v1/models from the router.
|
||||||
|
# llama-server router uses the GGUF filename (without .gguf) as the model id.
|
||||||
|
llm_router_expected_model_id: "Qwen3.6-35B-A3B-UD-Q4_K_S"
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference-multimodel
|
||||||
|
|
||||||
|
# No --tags needed here: router.yml is included dynamically from main.yml
|
||||||
|
# whenever llm_router_enabled: true. The full role runs but the
|
||||||
|
# discover/models/systemd/verify phases are gated on their own vars
|
||||||
|
# (llm_qwen_service_enabled etc.) and are idempotent. The stale
|
||||||
|
# models.yml (Phi-4/Mistral download tasks) uses variables no longer
|
||||||
|
# defined — a follow-up cleanup task should update that file.
|
||||||
|
|
||||||
|
- name: "POST-VALIDATION SAFETY NET — ensure production service is running"
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: false
|
||||||
|
become: true
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
# Always run this, regardless of whether the validation play succeeded.
|
||||||
|
# If the router.yml play stopped llama-server-qwen for VRAM validation
|
||||||
|
# and then a gate failed (play aborted), this play ensures it comes back up.
|
||||||
|
- name: "Ensure llama-server-qwen (port 8002) is running after validation (always)"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-qwen
|
||||||
|
state: started
|
||||||
|
enabled: true
|
||||||
|
ignore_errors: true # don't fail if the unit doesn't exist
|
||||||
|
|
||||||
|
- name: "Verify production /health after safety-net restart"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://10.1.71.130:8002/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
register: llm_safety_net_health
|
||||||
|
failed_when: false
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Report production status (safety-net check)"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: >-
|
||||||
|
Safety-net: llama-server-qwen :8002 health check returned
|
||||||
|
{{ llm_safety_net_health.status | default('UNREACHABLE') }}.
|
||||||
|
{{ 'OK — production is up.' if (llm_safety_net_health.status | default(0) | int == 200)
|
||||||
|
else 'WARNING — production may not be healthy. Check manually.' }}
|
||||||
@@ -0,0 +1,6 @@
|
|||||||
|
---
|
||||||
|
- name: Deploy shared nginx reverse proxy and certbot
|
||||||
|
hosts: illuminations
|
||||||
|
become: true
|
||||||
|
roles:
|
||||||
|
- nginx-proxy
|
||||||
@@ -1,22 +1,17 @@
|
|||||||
---
|
---
|
||||||
# ------------------------------------------------------------------------------
|
# ============================================================================
|
||||||
# FILE: playbooks/day1_deploy_semaphore.yml
|
# day1_deploy_semaphore.yml
|
||||||
# DESCRIPTION: Deploys Semaphore on imagineering
|
# ----------------------------------------------------------------------------
|
||||||
# Runs: common → docker-host → semaphore
|
# Deploys SemaphoreUI + PostgreSQL on the imagineering host (figment).
|
||||||
|
# Run AFTER day0_linux_baseline.yml has been applied to the target.
|
||||||
#
|
#
|
||||||
# USAGE:
|
# Usage:
|
||||||
# ansible-playbook -i inventory.yml playbooks/day1_deploy_semaphore.yml
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_semaphore.yml
|
||||||
#
|
# ============================================================================
|
||||||
# SECRETS REQUIRED IN VAULT (group_vars/all/vault):
|
|
||||||
# vault_semaphore_database_password
|
|
||||||
# vault_semaphore_admin_password
|
|
||||||
# vault_semaphore_access_key_encryption
|
|
||||||
# ------------------------------------------------------------------------------
|
|
||||||
|
|
||||||
- name: Deploy Semaphore
|
- name: Deploy SemaphoreUI on imagineering
|
||||||
hosts: semaphore_server
|
hosts: semaphore_server
|
||||||
become: true
|
become: true
|
||||||
|
gather_facts: true
|
||||||
roles:
|
roles:
|
||||||
- docker-host
|
|
||||||
- semaphore
|
- semaphore
|
||||||
@@ -0,0 +1,18 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day1_deploy_vllm.yml
|
||||||
|
# Deploy vLLM to a target host via roles/deploy-vllm.
|
||||||
|
#
|
||||||
|
# Staging run (deploy + validate WITHOUT touching production traffic):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_vllm.yml --limit astro-orbiter
|
||||||
|
#
|
||||||
|
# Cutover run (once staging is validated and Ryan/JARVIS approve flipping
|
||||||
|
# traffic — starts and enables the systemd unit(s), runs Phase 5 verification):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day1_deploy_vllm.yml \
|
||||||
|
# --limit astro-orbiter --extra-vars "vllm_service_state=started"
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
- name: Deploy vLLM inference serving stack
|
||||||
|
hosts: astro-orbiter
|
||||||
|
become: false
|
||||||
|
gather_facts: true
|
||||||
|
roles:
|
||||||
|
- deploy-vllm
|
||||||
@@ -0,0 +1,259 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day2_add_coder_alias.yml
|
||||||
|
# DESCRIPTION: Add Qwen2.5-Coder-14B-Instruct-Q4_K_M to the llama-server-router
|
||||||
|
# on astro-orbiter (10.1.71.130:8002).
|
||||||
|
#
|
||||||
|
# Context (t_55c164f5, 2026-08-13):
|
||||||
|
# Ryan requested a Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf be added to the
|
||||||
|
# astro-orbiter router with:
|
||||||
|
# alias = "Qwen2.5-Coder-14B-Instruct-4bit"
|
||||||
|
# n_gpu_layers = 99
|
||||||
|
# ctx_size = 16384
|
||||||
|
# flash_attn = true
|
||||||
|
# Deployed GitOps-style via this role; no hand-editing of the live preset.
|
||||||
|
#
|
||||||
|
# What this playbook does:
|
||||||
|
# 1. Downloads Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf into /opt/models if
|
||||||
|
# not already present (idempotent: size-check guard, no re-pull on match).
|
||||||
|
# 2. Redeploys the preset INI (adding the [Qwen2.5-Coder-14B-Instruct-Q4_K_M]
|
||||||
|
# section with alias = Qwen2.5-Coder-14B-Instruct-4bit).
|
||||||
|
# 3. Restarts llama-server-router to pick up the new model entry.
|
||||||
|
# 4. Verifies /v1/models returns all 4 models including the new Coder entry.
|
||||||
|
#
|
||||||
|
# VRAM context note (t_55c164f5):
|
||||||
|
# Qwen2.5-Coder-14B Q4_K_M: ~8.4GB weights + ~0.6GB KV @ 16K ctx ≈ 9.0GB
|
||||||
|
# Qwen3.6-35B-A3B: ~21.5GB
|
||||||
|
# Full co-residency is impossible on 24GB. LRU eviction handles this:
|
||||||
|
# when Coder is requested, Qwen3.6-35B is evicted (and vice versa).
|
||||||
|
# Model-switching incurs ~30-60s cold-load latency — expected and acceptable.
|
||||||
|
# Phi (~4.3GB) or Llama (~5.6GB) can co-reside with Coder (total ~14GB).
|
||||||
|
#
|
||||||
|
# Usage (from ~/git/homelab/ansible):
|
||||||
|
# env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook -i inventory.yml \
|
||||||
|
# playbooks/day2_add_coder_alias.yml
|
||||||
|
#
|
||||||
|
# Semaphore note: Semaphore SSH key for jarvis user is not loaded in the
|
||||||
|
# container (known pitfall, homelab-llm-serving skill). Run via CLI with
|
||||||
|
# id_jarvis key; document as exception per Ryan's standing CLI fallback directive.
|
||||||
|
#
|
||||||
|
# Author: War Machine (2026-08-13, t_55c164f5)
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Add Qwen2.5-Coder-14B-Instruct-4bit alias to astro-orbiter router"
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: false
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# Activate preset mode
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
llm_router_preset_path: /opt/llama-server-router-preset.ini
|
||||||
|
|
||||||
|
# Production port (router is on 8002 since t_cd0d5388)
|
||||||
|
llm_router_port: 8002
|
||||||
|
|
||||||
|
# Per-model ctx-size settings (carried from t_ryan_per_model_ctx; Coder new)
|
||||||
|
llm_router_llama_ctx_size: 8192
|
||||||
|
llm_router_llama_flash_attn: "true"
|
||||||
|
llm_router_phi_ctx_size: 32768
|
||||||
|
llm_router_phi_flash_attn: "true"
|
||||||
|
llm_router_coder_ctx_size: 16384
|
||||||
|
llm_router_coder_flash_attn: "true"
|
||||||
|
|
||||||
|
# All other vars inherit from host_vars + defaults/main.yml.
|
||||||
|
# Explicitly set the ones needed by the unit/template tasks for clarity:
|
||||||
|
llm_router_enabled: true
|
||||||
|
llm_service_user: jarvis
|
||||||
|
llm_binary_path: /opt/llama.cpp/build/bin/llama-server
|
||||||
|
llm_models_dir: /opt/models
|
||||||
|
llm_bind_address: "10.1.71.130"
|
||||||
|
llm_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_router_service_name: llama-server-router
|
||||||
|
llm_router_bind_address: "10.1.71.130"
|
||||||
|
llm_router_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_router_models_dir: /opt/models
|
||||||
|
llm_router_models_max: 4 # from host_vars; bumped by t_33acbb2e
|
||||||
|
llm_router_ctx_size: 65536 # Qwen3.6-35B default; per-model overrides above
|
||||||
|
llm_router_parallel: 1
|
||||||
|
llm_router_gpu_layers: 99
|
||||||
|
llm_router_batch_size: 2048
|
||||||
|
llm_router_ubatch_size: 512
|
||||||
|
llm_router_cache_type_k: q4_0
|
||||||
|
llm_router_cache_type_v: q4_0
|
||||||
|
llm_router_flash_attn: "auto"
|
||||||
|
llm_router_expected_model_id: "Qwen3.6-35B-A3B-UD-Q4_K_S"
|
||||||
|
llm_router_vram_max_mib: 23000
|
||||||
|
|
||||||
|
# Coder model staging entry (used below)
|
||||||
|
coder_filename: "Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf"
|
||||||
|
coder_url: "https://huggingface.co/bartowski/Qwen2.5-Coder-14B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-14B-Instruct-Q4_K_M.gguf"
|
||||||
|
coder_size_bytes: 8988111072
|
||||||
|
|
||||||
|
handlers:
|
||||||
|
- name: reload systemd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
daemon_reload: true
|
||||||
|
become: true
|
||||||
|
listen: "reload systemd"
|
||||||
|
|
||||||
|
- name: restart router
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-router
|
||||||
|
state: restarted
|
||||||
|
become: true
|
||||||
|
listen: "restart router"
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 1: Download Coder GGUF if not present / size mismatch
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[coder] Stat existing GGUF"
|
||||||
|
ansible.builtin.stat:
|
||||||
|
path: "{{ llm_models_dir }}/{{ coder_filename }}"
|
||||||
|
get_checksum: false
|
||||||
|
register: coder_stat
|
||||||
|
|
||||||
|
- name: "[coder] Download GGUF (skip if present and size matches)"
|
||||||
|
ansible.builtin.get_url:
|
||||||
|
url: "{{ coder_url }}"
|
||||||
|
dest: "{{ llm_models_dir }}/{{ coder_filename }}"
|
||||||
|
owner: "{{ llm_service_user }}"
|
||||||
|
group: "{{ llm_service_user }}"
|
||||||
|
mode: "0644"
|
||||||
|
timeout: 3600
|
||||||
|
when: >
|
||||||
|
not coder_stat.stat.exists or
|
||||||
|
coder_stat.stat.size != coder_size_bytes
|
||||||
|
register: coder_download
|
||||||
|
notify: restart router
|
||||||
|
|
||||||
|
- name: "[coder] Confirm GGUF size post-download"
|
||||||
|
ansible.builtin.stat:
|
||||||
|
path: "{{ llm_models_dir }}/{{ coder_filename }}"
|
||||||
|
get_checksum: false
|
||||||
|
register: coder_stat_post
|
||||||
|
|
||||||
|
- name: "[coder] FAIL if GGUF size mismatch after download"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
GGUF size mismatch: expected {{ coder_size_bytes }} bytes,
|
||||||
|
got {{ coder_stat_post.stat.size }} bytes.
|
||||||
|
Re-download may be needed.
|
||||||
|
when: coder_stat_post.stat.size != coder_size_bytes
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 2: Deploy updated preset INI (adds Coder section)
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[coder] Deploy preset INI to {{ llm_router_preset_path }}"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2"
|
||||||
|
dest: "{{ llm_router_preset_path }}"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: coder_preset_deployed
|
||||||
|
notify: restart router
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 3: Redeploy systemd unit (unchanged flags, but ensures unit is fresh)
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[coder] Deploy llama-server-router unit"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router.service.j2"
|
||||||
|
dest: /etc/systemd/system/llama-server-router.service
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: coder_unit_deployed
|
||||||
|
notify:
|
||||||
|
- reload systemd
|
||||||
|
- restart router
|
||||||
|
|
||||||
|
- name: "[coder] Flush handlers (daemon-reload + router restart)"
|
||||||
|
ansible.builtin.meta: flush_handlers
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 4: Verify router is up and Coder model appears in /v1/models
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[coder] Wait for /health (router supervisor)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
retries: 12
|
||||||
|
delay: 5
|
||||||
|
register: coder_health
|
||||||
|
until: coder_health.status == 200
|
||||||
|
|
||||||
|
- name: "[coder] Query /v1/models"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/models"
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 30
|
||||||
|
register: coder_models
|
||||||
|
|
||||||
|
- name: "[coder] Extract model IDs and aliases"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
coder_model_ids: "{{ coder_models.json.data | map(attribute='id') | list }}"
|
||||||
|
coder_all_aliases: "{{ coder_models.json.data | map(attribute='aliases') | flatten | list }}"
|
||||||
|
|
||||||
|
- name: "[coder] FAIL if Coder primary ID missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
'Qwen2.5-Coder-14B-Instruct-Q4_K_M' not in /v1/models.
|
||||||
|
IDs: {{ coder_model_ids }}
|
||||||
|
when: "'Qwen2.5-Coder-14B-Instruct-Q4_K_M' not in coder_model_ids"
|
||||||
|
|
||||||
|
- name: "[coder] FAIL if Coder alias missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
'Qwen2.5-Coder-14B-Instruct-4bit' not found as ID or alias in /v1/models.
|
||||||
|
IDs: {{ coder_model_ids }}
|
||||||
|
Aliases: {{ coder_all_aliases }}
|
||||||
|
when:
|
||||||
|
- "'Qwen2.5-Coder-14B-Instruct-4bit' not in coder_model_ids"
|
||||||
|
- "'Qwen2.5-Coder-14B-Instruct-4bit' not in coder_all_aliases"
|
||||||
|
|
||||||
|
- name: "[coder] FAIL if Qwen3.6-35B missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Qwen3.6-35B-A3B-UD-Q4_K_S' not in /v1/models. IDs: {{ coder_model_ids }}"
|
||||||
|
when: "'Qwen3.6-35B-A3B-UD-Q4_K_S' not in coder_model_ids"
|
||||||
|
|
||||||
|
- name: "[coder] FAIL if Phi missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Phi-3.5-mini-instruct-Q8_0' not in /v1/models. IDs: {{ coder_model_ids }}"
|
||||||
|
when: "'Phi-3.5-mini-instruct-Q8_0' not in coder_model_ids"
|
||||||
|
|
||||||
|
- name: "[coder] FAIL if Llama missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Meta-Llama-3.1-8B-Instruct-Q4_K_M' not in /v1/models. IDs: {{ coder_model_ids }}"
|
||||||
|
when: "'Meta-Llama-3.1-8B-Instruct-Q4_K_M' not in coder_model_ids"
|
||||||
|
|
||||||
|
- name: "[coder] PASS — full /v1/models summary"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "========================================================================"
|
||||||
|
- "QWEN2.5-CODER-14B ALIAS DEPLOYMENT — COMPLETE"
|
||||||
|
- ""
|
||||||
|
- " Mode: --models-preset ({{ llm_router_preset_path }})"
|
||||||
|
- " Service: llama-server-router.service (:{{ llm_router_port }})"
|
||||||
|
- ""
|
||||||
|
- " /v1/models IDs: {{ coder_model_ids }}"
|
||||||
|
- " /v1/models aliases: {{ coder_all_aliases }}"
|
||||||
|
- ""
|
||||||
|
- " VERIFY:"
|
||||||
|
- " Qwen3.6-35B-A3B-UD-Q4_K_S: {{ 'PRESENT' if 'Qwen3.6-35B-A3B-UD-Q4_K_S' in coder_model_ids else 'MISSING' }}"
|
||||||
|
- " Phi-3.5-mini-instruct-Q8_0: {{ 'PRESENT' if 'Phi-3.5-mini-instruct-Q8_0' in coder_model_ids else 'MISSING' }}"
|
||||||
|
- " Meta-Llama-3.1-8B-Instruct-Q4_K_M: {{ 'PRESENT' if 'Meta-Llama-3.1-8B-Instruct-Q4_K_M' in coder_model_ids else 'MISSING' }}"
|
||||||
|
- " Qwen2.5-Coder-14B-Instruct-Q4_K_M: {{ 'PRESENT' if 'Qwen2.5-Coder-14B-Instruct-Q4_K_M' in coder_model_ids else 'MISSING' }}"
|
||||||
|
- " Qwen2.5-Coder-14B-Instruct-4bit: {{ 'PRESENT (ID)' if 'Qwen2.5-Coder-14B-Instruct-4bit' in coder_model_ids else ('PRESENT (alias)' if 'Qwen2.5-Coder-14B-Instruct-4bit' in coder_all_aliases else 'MISSING') }}"
|
||||||
|
- ""
|
||||||
|
- " GGUF download: {{ 'NEW DOWNLOAD' if (coder_download is defined and coder_download.changed) else 'ALREADY PRESENT (skipped)' }}"
|
||||||
|
- "========================================================================"
|
||||||
@@ -0,0 +1,313 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day2_add_nomic_embed.yml
|
||||||
|
# DESCRIPTION: Add nomic-embed-text-v1.5-Q4_K_M to the llama-server-router
|
||||||
|
# on astro-orbiter (10.1.71.130:8002).
|
||||||
|
#
|
||||||
|
# Context (t_34b96e83, 2026-08-13, OpenViking Phase 1b):
|
||||||
|
# Ryan approved adding nomic-embed-text-v1.5-Q4_K_M as an embedding model
|
||||||
|
# after Phase 0 follow-up confirmed embedding models fold cleanly into the
|
||||||
|
# existing router preset via embedding=true. Model ID is "nomic-embed-text-v1.5".
|
||||||
|
# No alias needed — peter-parker and Honcho consumers will call it by the section
|
||||||
|
# name directly.
|
||||||
|
#
|
||||||
|
# What this playbook does:
|
||||||
|
# 1. Downloads nomic-embed-text-v1.5-Q4_K_M.gguf into /opt/models if not
|
||||||
|
# already present (idempotent: exact size-check guard, no re-pull on match).
|
||||||
|
# 2. Redeploys the preset INI (adding the [nomic-embed-text-v1.5] section with
|
||||||
|
# embedding=true, n-gpu-layers=99, ctx-size=8192, load-on-startup=true,
|
||||||
|
# sleep-idle-seconds=-1).
|
||||||
|
# 3. Restarts llama-server-router to pick up the new model entry.
|
||||||
|
# 4. Verifies /v1/models returns all 5 models including the new nomic entry.
|
||||||
|
# 5. Runs a /v1/embeddings smoke test to confirm the model actually embeds.
|
||||||
|
#
|
||||||
|
# VRAM context note (t_34b96e83):
|
||||||
|
# nomic-embed-text-v1.5 Q4_K_M: ~84MB weights, embedding model (no KV cache).
|
||||||
|
# VRAM impact is negligible — always pinned via sleep-idle-seconds=-1.
|
||||||
|
# The 4 generative models remain unchanged (OOM analysis unchanged from t_55c164f5).
|
||||||
|
#
|
||||||
|
# Usage (from ~/git/homelab/ansible):
|
||||||
|
# env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook -i inventory.yml \
|
||||||
|
# playbooks/day2_add_nomic_embed.yml
|
||||||
|
#
|
||||||
|
# Semaphore note: Semaphore SSH key for jarvis user is not loaded in the
|
||||||
|
# container (known pitfall, homelab-llm-serving skill). Run via CLI with
|
||||||
|
# id_jarvis key; document as exception per Ryan's standing CLI fallback directive.
|
||||||
|
#
|
||||||
|
# Author: War Machine (2026-08-13, t_34b96e83)
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Add nomic-embed-text-v1.5 embedding model to astro-orbiter router"
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: false
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# Activate preset mode
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
llm_router_preset_path: /opt/llama-server-router-preset.ini
|
||||||
|
|
||||||
|
# Production port (router is on 8002 since t_cd0d5388)
|
||||||
|
llm_router_port: 8002
|
||||||
|
|
||||||
|
# Per-model ctx-size settings (carried from t_55c164f5; nomic new)
|
||||||
|
llm_router_llama_ctx_size: 8192
|
||||||
|
llm_router_llama_flash_attn: "true"
|
||||||
|
llm_router_phi_ctx_size: 32768
|
||||||
|
llm_router_phi_flash_attn: "true"
|
||||||
|
llm_router_coder_ctx_size: 16384
|
||||||
|
llm_router_coder_flash_attn: "true"
|
||||||
|
llm_router_nomic_ctx_size: 8192
|
||||||
|
# NOTE (2026-08-14, t_openviking_embed_batch): per-model batch-size/
|
||||||
|
# ubatch-size lines in the preset INI are NOT honored by llama-server's
|
||||||
|
# router — only ctx-size is applied per-model; batch-size/ubatch-size for
|
||||||
|
# every spawned child come from the router's own global CLI flags
|
||||||
|
# (confirmed via `ps aux` on astro-orbiter: child process launched with
|
||||||
|
# the router's --batch-size/--ubatch-size regardless of the INI values).
|
||||||
|
# Kept below for documentation/future-proofing but the REAL fix is the
|
||||||
|
# global llm_router_batch_size / llm_router_ubatch_size override further
|
||||||
|
# down, which raises the physical batch for ALL models on this router
|
||||||
|
# (Qwen3.6-35B, Phi, Llama, Coder, nomic).
|
||||||
|
llm_router_nomic_batch_size: 4096
|
||||||
|
llm_router_nomic_ubatch_size: 4096
|
||||||
|
|
||||||
|
# All other vars inherit from host_vars + defaults/main.yml.
|
||||||
|
llm_router_enabled: true
|
||||||
|
llm_service_user: jarvis
|
||||||
|
llm_binary_path: /opt/llama.cpp/build/bin/llama-server
|
||||||
|
llm_models_dir: /opt/models
|
||||||
|
llm_bind_address: "10.1.71.130"
|
||||||
|
llm_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_router_service_name: llama-server-router
|
||||||
|
llm_router_bind_address: "10.1.71.130"
|
||||||
|
llm_router_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_router_models_dir: /opt/models
|
||||||
|
llm_router_models_max: 4 # from host_vars; bumped by t_33acbb2e
|
||||||
|
llm_router_ctx_size: 65536 # Qwen3.6-35B default; per-model overrides above
|
||||||
|
llm_router_parallel: 1
|
||||||
|
llm_router_gpu_layers: 99
|
||||||
|
# FIX (2026-08-14, t_openviking_embed_batch): raised from 512 to 4096.
|
||||||
|
# This is a GLOBAL router flag applied to every spawned model process
|
||||||
|
# (per-model INI batch-size/ubatch-size overrides are not honored by
|
||||||
|
# llama-server's router — see note above nomic vars). 512 tokens was too
|
||||||
|
# small for OpenViking's chunked-document embedding inputs (observed
|
||||||
|
# 2000-3400 tokens/chunk), causing hard 500 errors ("input (N tokens) is
|
||||||
|
# too large to process") that tripped OpenViking's circuit breaker into a
|
||||||
|
# permanent fail/re-enqueue loop. 4096 comfortably covers observed chunk
|
||||||
|
# sizes and stays under nomic's ctx-size=8192. VRAM impact of raising
|
||||||
|
# ubatch-size is in compute-buffer scratch space, not KV cache; monitored
|
||||||
|
# post-deploy against the 23000 MiB budget (host_vars/astro-orbiter).
|
||||||
|
llm_router_batch_size: 4096
|
||||||
|
llm_router_ubatch_size: 4096
|
||||||
|
llm_router_cache_type_k: q4_0
|
||||||
|
llm_router_cache_type_v: q4_0
|
||||||
|
llm_router_flash_attn: "auto"
|
||||||
|
llm_router_expected_model_id: "Qwen3.6-35B-A3B-UD-Q4_K_S"
|
||||||
|
llm_router_vram_max_mib: 23000
|
||||||
|
|
||||||
|
# nomic model staging
|
||||||
|
nomic_filename: "nomic-embed-text-v1.5-Q4_K_M.gguf"
|
||||||
|
nomic_url: "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.Q4_K_M.gguf"
|
||||||
|
nomic_size_bytes: 84106624
|
||||||
|
|
||||||
|
handlers:
|
||||||
|
- name: reload systemd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
daemon_reload: true
|
||||||
|
become: true
|
||||||
|
listen: "reload systemd"
|
||||||
|
|
||||||
|
- name: restart router
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-router
|
||||||
|
state: restarted
|
||||||
|
become: true
|
||||||
|
listen: "restart router"
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 1: Download nomic GGUF if not present / size mismatch
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[nomic] Stat existing GGUF"
|
||||||
|
ansible.builtin.stat:
|
||||||
|
path: "{{ llm_models_dir }}/{{ nomic_filename }}"
|
||||||
|
get_checksum: false
|
||||||
|
register: nomic_stat
|
||||||
|
|
||||||
|
- name: "[nomic] Download GGUF (skip if present and size matches)"
|
||||||
|
ansible.builtin.get_url:
|
||||||
|
url: "{{ nomic_url }}"
|
||||||
|
dest: "{{ llm_models_dir }}/{{ nomic_filename }}"
|
||||||
|
owner: "{{ llm_service_user }}"
|
||||||
|
group: "{{ llm_service_user }}"
|
||||||
|
mode: "0644"
|
||||||
|
timeout: 300
|
||||||
|
when: >
|
||||||
|
not nomic_stat.stat.exists or
|
||||||
|
nomic_stat.stat.size != nomic_size_bytes
|
||||||
|
register: nomic_download
|
||||||
|
notify: restart router
|
||||||
|
|
||||||
|
- name: "[nomic] Confirm GGUF size post-download"
|
||||||
|
ansible.builtin.stat:
|
||||||
|
path: "{{ llm_models_dir }}/{{ nomic_filename }}"
|
||||||
|
get_checksum: false
|
||||||
|
register: nomic_stat_post
|
||||||
|
|
||||||
|
- name: "[nomic] FAIL if GGUF size mismatch after download"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
GGUF size mismatch: expected {{ nomic_size_bytes }} bytes,
|
||||||
|
got {{ nomic_stat_post.stat.size }} bytes.
|
||||||
|
Re-download may be needed.
|
||||||
|
when: nomic_stat_post.stat.size != nomic_size_bytes
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 2: Deploy updated preset INI (adds nomic-embed-text-v1.5 section)
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[nomic] Deploy preset INI to {{ llm_router_preset_path }}"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2"
|
||||||
|
dest: "{{ llm_router_preset_path }}"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: nomic_preset_deployed
|
||||||
|
notify: restart router
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 3: Redeploy systemd unit (ensures unit is fresh; no flag changes)
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[nomic] Deploy llama-server-router unit"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router.service.j2"
|
||||||
|
dest: /etc/systemd/system/llama-server-router.service
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: nomic_unit_deployed
|
||||||
|
notify:
|
||||||
|
- reload systemd
|
||||||
|
- restart router
|
||||||
|
|
||||||
|
- name: "[nomic] Flush handlers (daemon-reload + router restart)"
|
||||||
|
ansible.builtin.meta: flush_handlers
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 4: Verify router is up and nomic model appears in /v1/models
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[nomic] Wait for /health (router supervisor)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
retries: 12
|
||||||
|
delay: 5
|
||||||
|
register: nomic_health
|
||||||
|
until: nomic_health.status == 200
|
||||||
|
|
||||||
|
- name: "[nomic] Query /v1/models"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/models"
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 30
|
||||||
|
register: nomic_models
|
||||||
|
|
||||||
|
- name: "[nomic] Extract model IDs and aliases"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
nomic_model_ids: "{{ nomic_models.json.data | map(attribute='id') | list }}"
|
||||||
|
nomic_all_aliases: "{{ nomic_models.json.data | map(attribute='aliases') | flatten | list }}"
|
||||||
|
|
||||||
|
- name: "[nomic] FAIL if nomic primary ID missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
'nomic-embed-text-v1.5' not in /v1/models.
|
||||||
|
IDs: {{ nomic_model_ids }}
|
||||||
|
when: "'nomic-embed-text-v1.5' not in nomic_model_ids"
|
||||||
|
|
||||||
|
- name: "[nomic] FAIL if Qwen3.6-35B missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Qwen3.6-35B-A3B-UD-Q4_K_S' not in /v1/models. IDs: {{ nomic_model_ids }}"
|
||||||
|
when: "'Qwen3.6-35B-A3B-UD-Q4_K_S' not in nomic_model_ids"
|
||||||
|
|
||||||
|
- name: "[nomic] FAIL if Phi missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Phi-3.5-mini-instruct-Q8_0' not in /v1/models. IDs: {{ nomic_model_ids }}"
|
||||||
|
when: "'Phi-3.5-mini-instruct-Q8_0' not in nomic_model_ids"
|
||||||
|
|
||||||
|
- name: "[nomic] FAIL if Llama missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Meta-Llama-3.1-8B-Instruct-Q4_K_M' not in /v1/models. IDs: {{ nomic_model_ids }}"
|
||||||
|
when: "'Meta-Llama-3.1-8B-Instruct-Q4_K_M' not in nomic_model_ids"
|
||||||
|
|
||||||
|
- name: "[nomic] FAIL if Coder missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Qwen2.5-Coder-14B-Instruct-Q4_K_M' not in /v1/models. IDs: {{ nomic_model_ids }}"
|
||||||
|
when: "'Qwen2.5-Coder-14B-Instruct-Q4_K_M' not in nomic_model_ids"
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 5: /v1/embeddings smoke test — confirm model actually embeds
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[nomic] POST /v1/embeddings smoke test"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/embeddings"
|
||||||
|
method: POST
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "nomic-embed-text-v1.5"
|
||||||
|
input: "The dog ran across the park."
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 120
|
||||||
|
register: nomic_embed_result
|
||||||
|
|
||||||
|
- name: "[nomic] Extract embedding vector length"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
nomic_embed_dims: >-
|
||||||
|
{{ (nomic_embed_result.json.data | first).embedding | length }}
|
||||||
|
when:
|
||||||
|
- nomic_embed_result.status == 200
|
||||||
|
- nomic_embed_result.json.data is defined
|
||||||
|
- nomic_embed_result.json.data | length > 0
|
||||||
|
|
||||||
|
- name: "[nomic] FAIL if embedding vector is empty or missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
Embedding smoke test returned no vector.
|
||||||
|
Response: {{ nomic_embed_result.json }}
|
||||||
|
when: >-
|
||||||
|
nomic_embed_result.status != 200 or
|
||||||
|
nomic_embed_result.json.data is not defined or
|
||||||
|
nomic_embed_result.json.data | length == 0 or
|
||||||
|
(nomic_embed_result.json.data | first).embedding | length == 0
|
||||||
|
|
||||||
|
- name: "[nomic] PASS — full summary"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "========================================================================"
|
||||||
|
- "NOMIC-EMBED-TEXT-V1.5 DEPLOYMENT — COMPLETE"
|
||||||
|
- ""
|
||||||
|
- " Mode: --models-preset ({{ llm_router_preset_path }})"
|
||||||
|
- " Service: llama-server-router.service (:{{ llm_router_port }})"
|
||||||
|
- ""
|
||||||
|
- " /v1/models IDs: {{ nomic_model_ids }}"
|
||||||
|
- ""
|
||||||
|
- " VERIFY:"
|
||||||
|
- " Qwen3.6-35B-A3B-UD-Q4_K_S: {{ 'PRESENT' if 'Qwen3.6-35B-A3B-UD-Q4_K_S' in nomic_model_ids else 'MISSING' }}"
|
||||||
|
- " Phi-3.5-mini-instruct-Q8_0: {{ 'PRESENT' if 'Phi-3.5-mini-instruct-Q8_0' in nomic_model_ids else 'MISSING' }}"
|
||||||
|
- " Meta-Llama-3.1-8B-Instruct-Q4_K_M: {{ 'PRESENT' if 'Meta-Llama-3.1-8B-Instruct-Q4_K_M' in nomic_model_ids else 'MISSING' }}"
|
||||||
|
- " Qwen2.5-Coder-14B-Instruct-Q4_K_M: {{ 'PRESENT' if 'Qwen2.5-Coder-14B-Instruct-Q4_K_M' in nomic_model_ids else 'MISSING' }}"
|
||||||
|
- " nomic-embed-text-v1.5: {{ 'PRESENT' if 'nomic-embed-text-v1.5' in nomic_model_ids else 'MISSING' }}"
|
||||||
|
- ""
|
||||||
|
- " Embedding smoke test: PASS"
|
||||||
|
- " Vector dimensions: {{ nomic_embed_dims | default('unknown') }}"
|
||||||
|
- ""
|
||||||
|
- " GGUF download: {{ 'NEW DOWNLOAD' if (nomic_download is defined and nomic_download.changed) else 'ALREADY PRESENT (skipped)' }}"
|
||||||
|
- "========================================================================"
|
||||||
@@ -0,0 +1,203 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day2_add_phi_alias.yml
|
||||||
|
# DESCRIPTION: Add Phi-3.5-mini-instruct-8bit alias to the llama-server-router
|
||||||
|
# by switching from --models-dir to --models-preset INI mode.
|
||||||
|
#
|
||||||
|
# Context (t_9adf0889, 2026-08-12):
|
||||||
|
# Ryan's Hermes config (auxiliary.title_generation.model) points to
|
||||||
|
# "Phi-3.5-mini-instruct-8bit" but the router only exposes the GGUF
|
||||||
|
# filename-derived ID "Phi-3.5-mini-instruct-Q8_0". They are the same file.
|
||||||
|
# This playbook adds the alias so both names work without changing Ryan's
|
||||||
|
# Hermes config.
|
||||||
|
#
|
||||||
|
# What this playbook does:
|
||||||
|
# 1. Deploys the preset INI template (llama-server-router-preset.ini.j2)
|
||||||
|
# to /opt/llama-server-router-preset.ini on astro-orbiter.
|
||||||
|
# 2. Redeploys the systemd unit (llama-server-router.service) with
|
||||||
|
# --models-preset instead of --models-dir.
|
||||||
|
# 3. Restarts llama-server-router to pick up the new flag.
|
||||||
|
# 4. Verifies that /v1/models returns:
|
||||||
|
# - Phi-3.5-mini-instruct-Q8_0 (original ID — must still work)
|
||||||
|
# - Phi-3.5-mini-instruct-8bit (new alias — Ryan's config target)
|
||||||
|
# - Qwen3.6-35B-A3B-UD-Q4_K_S (unchanged)
|
||||||
|
# - Meta-Llama-3.1-8B-Instruct-Q4_K_M (unchanged)
|
||||||
|
#
|
||||||
|
# Known upstream behavior:
|
||||||
|
# GH #22364: --models-preset creates an extra "default" entry in /v1/models.
|
||||||
|
# This is cosmetic only and does not affect model selection by name.
|
||||||
|
#
|
||||||
|
# Usage (from ~/git/homelab/ansible):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day2_add_phi_alias.yml
|
||||||
|
#
|
||||||
|
# Semaphore note (t_9adf0889): Semaphore SSH key for jarvis user is not loaded
|
||||||
|
# in the container (known pitfall, homelab-llm-serving skill). Run via CLI with
|
||||||
|
# id_jarvis key; document as exception per Ryan's standing CLI fallback directive.
|
||||||
|
#
|
||||||
|
# Author: War Machine (2026-08-12, t_9adf0889)
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Add Phi-3.5-mini-instruct-8bit alias — switch router to preset mode"
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: false
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# Activate preset mode and provide the on-disk INI path
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
llm_router_preset_path: /opt/llama-server-router-preset.ini
|
||||||
|
|
||||||
|
# Production port (router is already on 8002 since t_cd0d5388)
|
||||||
|
llm_router_port: 8002
|
||||||
|
|
||||||
|
# All other vars inherit from host_vars + defaults/main.yml.
|
||||||
|
# Explicitly set the ones needed by the unit template for clarity:
|
||||||
|
llm_router_enabled: true
|
||||||
|
llm_service_user: jarvis
|
||||||
|
llm_binary_path: /opt/llama.cpp/build/bin/llama-server
|
||||||
|
llm_models_dir: /opt/models
|
||||||
|
llm_bind_address: "10.1.71.130"
|
||||||
|
llm_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_router_service_name: llama-server-router
|
||||||
|
llm_router_bind_address: "10.1.71.130"
|
||||||
|
llm_router_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_router_models_dir: /opt/models
|
||||||
|
llm_router_models_max: 4 # from host_vars; bumped by t_33acbb2e
|
||||||
|
llm_router_ctx_size: 65536
|
||||||
|
llm_router_parallel: 1
|
||||||
|
llm_router_gpu_layers: 99
|
||||||
|
llm_router_batch_size: 2048
|
||||||
|
llm_router_ubatch_size: 512
|
||||||
|
llm_router_cache_type_k: q4_0
|
||||||
|
llm_router_cache_type_v: q4_0
|
||||||
|
llm_router_flash_attn: "auto"
|
||||||
|
llm_router_expected_model_id: "Qwen3.6-35B-A3B-UD-Q4_K_S"
|
||||||
|
llm_router_vram_max_mib: 23000
|
||||||
|
|
||||||
|
handlers:
|
||||||
|
- name: reload systemd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
daemon_reload: true
|
||||||
|
become: true
|
||||||
|
listen: "reload systemd"
|
||||||
|
|
||||||
|
- name: restart router
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-router
|
||||||
|
state: restarted
|
||||||
|
become: true
|
||||||
|
listen: "restart router"
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 1: Deploy the preset INI
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[phi-alias] Deploy preset INI to {{ llm_router_preset_path }}"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2"
|
||||||
|
dest: "{{ llm_router_preset_path }}"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: phi_alias_preset_deployed
|
||||||
|
notify:
|
||||||
|
- restart router
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 2: Redeploy systemd unit with --models-preset flag
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[phi-alias] Deploy llama-server-router unit (--models-preset mode)"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router.service.j2"
|
||||||
|
dest: /etc/systemd/system/llama-server-router.service
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: phi_alias_unit_deployed
|
||||||
|
notify:
|
||||||
|
- reload systemd
|
||||||
|
- restart router
|
||||||
|
|
||||||
|
- name: "[phi-alias] Flush handlers (daemon-reload + router restart)"
|
||||||
|
ansible.builtin.meta: flush_handlers
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 3: Verify alias is present
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[phi-alias] Wait for /health (router supervisor, no model needed)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
retries: 12
|
||||||
|
delay: 5
|
||||||
|
register: phi_alias_health
|
||||||
|
until: phi_alias_health.status == 200
|
||||||
|
|
||||||
|
- name: "[phi-alias] Query /v1/models"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/models"
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 30
|
||||||
|
register: phi_alias_models
|
||||||
|
|
||||||
|
- name: "[phi-alias] Extract model IDs and aliases"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
phi_alias_model_ids: "{{ phi_alias_models.json.data | map(attribute='id') | list }}"
|
||||||
|
phi_alias_all_aliases: "{{ phi_alias_models.json.data | map(attribute='aliases') | flatten | list }}"
|
||||||
|
phi_alias_model_sources: "{{ phi_alias_models.json.data | map(attribute='source') | list }}"
|
||||||
|
|
||||||
|
- name: "[phi-alias] FAIL if Phi original ID missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
'Phi-3.5-mini-instruct-Q8_0' not in /v1/models.
|
||||||
|
IDs: {{ phi_alias_model_ids }}
|
||||||
|
when: "'Phi-3.5-mini-instruct-Q8_0' not in phi_alias_model_ids"
|
||||||
|
|
||||||
|
- name: "[phi-alias] FAIL if Phi alias missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
'Phi-3.5-mini-instruct-8bit' not found as ID or alias in /v1/models.
|
||||||
|
IDs: {{ phi_alias_model_ids }}
|
||||||
|
Aliases: {{ phi_alias_all_aliases }}
|
||||||
|
when:
|
||||||
|
- "'Phi-3.5-mini-instruct-8bit' not in phi_alias_model_ids"
|
||||||
|
- "'Phi-3.5-mini-instruct-8bit' not in phi_alias_all_aliases"
|
||||||
|
|
||||||
|
- name: "[phi-alias] FAIL if Qwen missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Qwen3.6-35B-A3B-UD-Q4_K_S' not in /v1/models. IDs: {{ phi_alias_model_ids }}"
|
||||||
|
when: "'Qwen3.6-35B-A3B-UD-Q4_K_S' not in phi_alias_model_ids"
|
||||||
|
|
||||||
|
- name: "[phi-alias] FAIL if Llama missing"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "'Meta-Llama-3.1-8B-Instruct-Q4_K_M' not in /v1/models. IDs: {{ phi_alias_model_ids }}"
|
||||||
|
when: "'Meta-Llama-3.1-8B-Instruct-Q4_K_M' not in phi_alias_model_ids"
|
||||||
|
|
||||||
|
- name: "[phi-alias] PASS — full /v1/models summary"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "========================================================================"
|
||||||
|
- "PHI ALIAS DEPLOYMENT — COMPLETE"
|
||||||
|
- ""
|
||||||
|
- " Mode: --models-preset ({{ llm_router_preset_path }})"
|
||||||
|
- " Service: llama-server-router.service (:{{ llm_router_port }})"
|
||||||
|
- ""
|
||||||
|
- " /v1/models IDs: {{ phi_alias_model_ids }}"
|
||||||
|
- " /v1/models aliases: {{ phi_alias_all_aliases }}"
|
||||||
|
- " Sources: {{ phi_alias_model_sources }}"
|
||||||
|
- ""
|
||||||
|
- " VERIFY:"
|
||||||
|
- " Phi-3.5-mini-instruct-Q8_0: {{ 'PRESENT' if 'Phi-3.5-mini-instruct-Q8_0' in phi_alias_model_ids else 'MISSING' }}"
|
||||||
|
- " Phi-3.5-mini-instruct-8bit: {{ 'PRESENT (ID)' if 'Phi-3.5-mini-instruct-8bit' in phi_alias_model_ids else ('PRESENT (alias)' if 'Phi-3.5-mini-instruct-8bit' in phi_alias_all_aliases else 'MISSING') }}"
|
||||||
|
- " Qwen3.6-35B-A3B-UD-Q4_K_S: {{ 'PRESENT' if 'Qwen3.6-35B-A3B-UD-Q4_K_S' in phi_alias_model_ids else 'MISSING' }}"
|
||||||
|
- " Meta-Llama-3.1-8B-Instruct-Q4_K_M: {{ 'PRESENT' if 'Meta-Llama-3.1-8B-Instruct-Q4_K_M' in phi_alias_model_ids else 'MISSING' }}"
|
||||||
|
- ""
|
||||||
|
- " GH #22364: if 'default' appears in IDs above, that is expected"
|
||||||
|
- " in --models-preset mode. Cosmetic only."
|
||||||
|
- "========================================================================"
|
||||||
@@ -0,0 +1,161 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day2_bump_router_models_max.yml
|
||||||
|
# DESCRIPTION: Bump --models-max on the production llama-server-router unit.
|
||||||
|
#
|
||||||
|
# Context: t_33acbb2e (2026-08-12) — Ryan requested --models-max raised from 1
|
||||||
|
# to 4 so the router can keep multiple GGUFs resident on-demand (LRU eviction
|
||||||
|
# when the cap is reached). The actual var change lives in:
|
||||||
|
# host_vars/astro-orbiter/vars.yml (llm_router_models_max: 4)
|
||||||
|
#
|
||||||
|
# This playbook:
|
||||||
|
# 1. Re-renders llama-server-router.service.j2 with the updated var value.
|
||||||
|
# 2. Reloads systemd (daemon-reload handler) if the unit changed.
|
||||||
|
# 3. Restarts llama-server-router so the new --models-max takes effect on the
|
||||||
|
# live process. Router holds no resident model (all-unloaded) so restart
|
||||||
|
# is sub-second and non-disruptive.
|
||||||
|
# 4. Verifies /health returns 200 and /v1/models still lists all three GGUFs.
|
||||||
|
#
|
||||||
|
# VRAM NOTE: --models-max 4 allows up to all 3 current GGUFs to co-reside on
|
||||||
|
# a 24GB card simultaneously. Worst-case combined footprint is ~31GB which
|
||||||
|
# EXCEEDS 24GB — OOM is possible if all 3 are loaded concurrently. In normal
|
||||||
|
# single-user homelab operation this is very unlikely. Full VRAM breakdown
|
||||||
|
# documented in host_vars/astro-orbiter/vars.yml. Ryan approved (t_33acbb2e).
|
||||||
|
#
|
||||||
|
# Execution channel: Semaphore template "llm_router_update_unit" (project mk-labs).
|
||||||
|
# Do NOT run via direct ansible-playbook or ad-hoc ssh/systemctl.
|
||||||
|
#
|
||||||
|
# Author: War Machine (2026-08-12, t_33acbb2e)
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Bump llama-server-router --models-max to 4 on astro-orbiter"
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: true
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# Production vars — router is live on :8002 (post-cutover t_cd0d5388)
|
||||||
|
llm_router_port: 8002
|
||||||
|
llm_router_bind_address: "10.1.71.130"
|
||||||
|
|
||||||
|
# llm_router_models_max is 4 via host_vars/astro-orbiter/vars.yml.
|
||||||
|
# Remaining role vars come from host_vars + defaults/main.yml via the
|
||||||
|
# inventory — we only explicitly set vars this playbook needs for its
|
||||||
|
# own tasks (health/models check URIs).
|
||||||
|
|
||||||
|
# Needed by the template task (mirrors defaults set in role defaults/main.yml)
|
||||||
|
llm_service_user: jarvis
|
||||||
|
llm_binary_path: /opt/llama.cpp/build/bin/llama-server
|
||||||
|
llm_models_dir: /opt/models
|
||||||
|
llm_router_service_name: llama-server-router
|
||||||
|
llm_router_models_dir: /opt/models
|
||||||
|
llm_router_gpu_layers: 99
|
||||||
|
llm_router_ctx_size: 65536
|
||||||
|
llm_router_flash_attn: "auto"
|
||||||
|
llm_router_cache_type_k: q4_0
|
||||||
|
llm_router_cache_type_v: q4_0
|
||||||
|
llm_router_batch_size: 2048
|
||||||
|
llm_router_ubatch_size: 512
|
||||||
|
llm_router_parallel: 1
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
# Phase 1: Re-render the router unit file
|
||||||
|
# Template src path is relative to the role's templates/ dir; we reference
|
||||||
|
# it with a relative path that Ansible resolves from the role directory.
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Deploy updated llama-server-router unit (--models-max {{ llm_router_models_max }})"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "{{ playbook_dir }}/../roles/llm-inference-multimodel/templates/llama-server-router.service.j2"
|
||||||
|
dest: "/etc/systemd/system/{{ llm_router_service_name }}.service"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: llm_router_unit_updated
|
||||||
|
notify:
|
||||||
|
- reload systemd
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
- name: "Flush handlers — ensure daemon-reload lands before restart"
|
||||||
|
ansible.builtin.meta: flush_handlers
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
# Phase 2: Restart the router so the new --models-max takes effect.
|
||||||
|
# Always restart (even if unit unchanged) to ensure live process matches.
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Restart llama-server-router so --models-max {{ llm_router_models_max }} takes effect"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: "{{ llm_router_service_name }}"
|
||||||
|
state: restarted
|
||||||
|
enabled: true
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
# Phase 3: Verify /health returns 200
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Wait for /health to return 200 after restart"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
register: bump_health_check
|
||||||
|
retries: 10
|
||||||
|
delay: 3
|
||||||
|
until: bump_health_check.status == 200
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
# Phase 4: Verify /v1/models lists all three GGUFs
|
||||||
|
# -------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Check /v1/models — all three GGUFs should appear"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/models"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
return_content: true
|
||||||
|
register: bump_models_check
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
- name: "Display /v1/models summary"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "======================================================================"
|
||||||
|
- "--models-max BUMP VERIFICATION (t_33acbb2e)"
|
||||||
|
- ""
|
||||||
|
- " /health: HTTP {{ bump_health_check.status }}"
|
||||||
|
- " /v1/models HTTP: {{ bump_models_check.status }}"
|
||||||
|
- " Models listed: {{ bump_models_check.json.data | map(attribute='id') | list | join(', ') }}"
|
||||||
|
- ""
|
||||||
|
- " --models-max now: {{ llm_router_models_max }}"
|
||||||
|
- " --parallel (unchanged): {{ llm_router_parallel }}"
|
||||||
|
- ""
|
||||||
|
- " VRAM WARNING: worst-case 3-model co-residency ~31GB > 24GB RTX 3090."
|
||||||
|
- " OOM risk if all 3 load concurrently. LRU eviction mitigates in practice."
|
||||||
|
- " Full breakdown: host_vars/astro-orbiter/vars.yml"
|
||||||
|
- "======================================================================"
|
||||||
|
when: bump_models_check is defined
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
- name: "GATE: confirm all 3 expected GGUFs appear in /v1/models"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- "'Qwen3.6-35B-A3B-UD-Q4_K_S' in (bump_models_check.json.data | map(attribute='id') | list)"
|
||||||
|
- "'Phi-3.5-mini-instruct-Q8_0' in (bump_models_check.json.data | map(attribute='id') | list)"
|
||||||
|
- "'Meta-Llama-3.1-8B-Instruct-Q4_K_M' in (bump_models_check.json.data | map(attribute='id') | list)"
|
||||||
|
fail_msg: >-
|
||||||
|
/v1/models did not return all 3 expected GGUFs after --models-max bump.
|
||||||
|
Check router logs: journalctl -u llama-server-router -n 50
|
||||||
|
success_msg: "GATE PASSED: all 3 GGUFs listed in /v1/models."
|
||||||
|
when: bump_models_check is defined
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
handlers:
|
||||||
|
- name: reload systemd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
daemon_reload: true
|
||||||
|
listen: "reload systemd"
|
||||||
@@ -0,0 +1,59 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# Playbook: day2_cpu_offload_aux_models.yml
|
||||||
|
# Purpose: CPU-offload Qwen2.5-Coder-14B and Meta-Llama-3.1-8B on
|
||||||
|
# astro-orbiter's production router (port 8002).
|
||||||
|
#
|
||||||
|
# What this playbook does:
|
||||||
|
# 1. Re-renders llama-server-router-preset.ini (Coder + Llama sections now
|
||||||
|
# use per-model n-gpu-layers vars = 0 -> full CPU inference).
|
||||||
|
# 2. Re-renders the router unit (--models-max now 4 via host_vars, global
|
||||||
|
# --n-gpu-layers removed per t_72646029 unit template fix) and restarts
|
||||||
|
# llama-server-router so both changes take effect.
|
||||||
|
# 3. Verifies per the role's router_preset phase.
|
||||||
|
#
|
||||||
|
# Context (2026-08-17):
|
||||||
|
# - RAM/model-swap audit, TIER 1 (Coder-14B CPU offload) + TIER 2
|
||||||
|
# (Llama-3.1-8B CPU offload) — Ryan approved 1 & 2 on 2026-08-17.
|
||||||
|
# See inbox/ryan/2026-08-17-llm-system-ram-model-swap.md.
|
||||||
|
# - Unit template fix (t_72646029): global --n-gpu-layers removed from
|
||||||
|
# ExecStart in preset mode. Each INI section now sets n-gpu-layers
|
||||||
|
# explicitly (Qwen3.8=99, Phi=99, nomic=99, Coder=0, Llama=0).
|
||||||
|
# - Concurrent residency after change: Qwen3.8-27B (20,302 MiB @ 128K ctx)
|
||||||
|
# + nomic-embed (558 MiB, pinned) + Coder (CPU, ~1,390 MiB CUDA ctx) +
|
||||||
|
# Llama (CPU, ~1,706 MiB CUDA ctx) = ~24,004 MiB. NOTE: llama.cpp 6ea215d
|
||||||
|
# allocates CUDA-context VRAM even at n-gpu-layers=0, so CPU models are not
|
||||||
|
# 0-VRAM; total sits at the 24,576 MiB physical limit (headroom ~572 MiB).
|
||||||
|
# Qwen3.8 is never evicted for a CPU aux model; Phi-3.5-mini (GPU, 8.3GB)
|
||||||
|
# still evicts as before.
|
||||||
|
# - CPU speed (8-core Ryzen 7 5800XT): ~5-10 tok/s (14B), ~10-20 tok/s (8B).
|
||||||
|
# - Semaphore SSH gap for astro-orbiter still applies (t_730f9584 /
|
||||||
|
# t_33acbb2e); running direct CLI Ansible per standing exception.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# cd /home/hermes/git/homelab/ansible
|
||||||
|
# env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook \
|
||||||
|
# -i inventory.yml \
|
||||||
|
# playbooks/day2_cpu_offload_aux_models.yml
|
||||||
|
#
|
||||||
|
# Rollback:
|
||||||
|
# git checkout -- \
|
||||||
|
# roles/llm-inference-multimodel/templates/llama-server-router.service.j2 \
|
||||||
|
# roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2 \
|
||||||
|
# roles/llm-inference-multimodel/defaults/main.yml \
|
||||||
|
# host_vars/astro-orbiter/vars.yml
|
||||||
|
# (restores n-gpu-layers=99 global flag, models-max=2, all GPU)
|
||||||
|
# then re-run this playbook to redeploy rollback state.
|
||||||
|
# Note: playbooks/day2_cpu_offload_aux_models.yml is untracked — left on disk.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
- name: CPU-offload Coder-14B and Llama-3.1-8B on astro-orbiter
|
||||||
|
hosts: astro-orbiter
|
||||||
|
become: true
|
||||||
|
vars:
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
llm_router_enabled: true
|
||||||
|
llm_router_port: 8002
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference-multimodel
|
||||||
|
tags: [always]
|
||||||
@@ -0,0 +1,511 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day2_cutover_qwen_to_router.yml
|
||||||
|
# DESCRIPTION: Promote llama-server-router to production on port 8002.
|
||||||
|
#
|
||||||
|
# Context: Router-mode shadow deployment (t_0cca74a2) validated 2026-08-12:
|
||||||
|
# all 4 hard gates PASSED (n_ctx 65536, tool-calling PASS, hallucination-stress
|
||||||
|
# PASS, VRAM 20410 MiB / 1 process). Ryan approved cutover.
|
||||||
|
#
|
||||||
|
# This playbook makes the router the permanent production endpoint:
|
||||||
|
#
|
||||||
|
# 1. Stop + disable llama-server-qwen (:8002). Unit file is PRESERVED on disk
|
||||||
|
# as the rollback target (same pattern as prior role history).
|
||||||
|
# 2. Redeploy llama-server-router unit file with --port 8002 (production port).
|
||||||
|
# PORT DECISION: we rebind the router to :8002 rather than updating 8
|
||||||
|
# dependent Hermes profiles' base_url. One unit file change beats 8
|
||||||
|
# config.yaml updates — atomic, GitOps-clean, zero profile drift.
|
||||||
|
# 3. Enable + start llama-server-router on :8002.
|
||||||
|
# 4. Re-run validation gates 1-3 against the NOW-production endpoint.
|
||||||
|
# (Same logic as Phase R / router_verify in tasks/router.yml — hard gates.)
|
||||||
|
# 5. Run Gate 4: verify bundled SvelteKit UI is reachable.
|
||||||
|
#
|
||||||
|
# Usage (from ~/git/homelab/ansible):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day2_cutover_qwen_to_router.yml
|
||||||
|
#
|
||||||
|
# Rollback (if gates fail or any time after):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day2_cutover_qwen_to_router.yml \
|
||||||
|
# --tags cutover_rollback
|
||||||
|
#
|
||||||
|
# Author: War Machine (2026-08-12, t_cd0d5388)
|
||||||
|
# Approved by: Ryan (cutover authorization, 2026-08-12)
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "CUTOVER — Promote llama-server-router to production (:8002) on astro-orbiter"
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: true
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# ----------------------------------------------------------------
|
||||||
|
# PORT DECISION:
|
||||||
|
# We rebind the router to :8002 (production port) rather than
|
||||||
|
# updating 8 dependent Hermes profiles' base_url to :8003.
|
||||||
|
# Rationale: one unit file change is atomic and GitOps-clean.
|
||||||
|
# Updating 8 config.yaml files risks drift and requires per-profile
|
||||||
|
# activation tests. The template renders llm_router_port as the
|
||||||
|
# --port argument; we just override it here to 8002.
|
||||||
|
# ----------------------------------------------------------------
|
||||||
|
|
||||||
|
# Router port override: take over production port
|
||||||
|
llm_router_port: 8002
|
||||||
|
|
||||||
|
# All other role defaults needed by the template (mirrors defaults/main.yml)
|
||||||
|
llm_service_user: jarvis
|
||||||
|
llm_binary_path: /opt/llama.cpp/build/bin/llama-server
|
||||||
|
llm_models_dir: /opt/models
|
||||||
|
llm_bind_address: "10.1.71.130"
|
||||||
|
llm_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
|
||||||
|
llm_router_enabled: true
|
||||||
|
llm_router_service_name: llama-server-router
|
||||||
|
llm_router_models_dir: /opt/models
|
||||||
|
llm_router_models_max: 1 # CRITICAL: RTX 3090 24GB, single model only
|
||||||
|
llm_router_ctx_size: 65536
|
||||||
|
llm_router_parallel: 1
|
||||||
|
llm_router_gpu_layers: 99
|
||||||
|
llm_router_batch_size: 2048
|
||||||
|
llm_router_ubatch_size: 512
|
||||||
|
llm_router_cache_type_k: q4_0
|
||||||
|
llm_router_cache_type_v: q4_0
|
||||||
|
llm_router_flash_attn: "auto"
|
||||||
|
llm_router_bind_address: "10.1.71.130"
|
||||||
|
llm_router_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_router_expected_model_id: "Qwen3.6-35B-A3B-UD-Q4_K_S"
|
||||||
|
llm_router_vram_max_mib: 23000
|
||||||
|
|
||||||
|
llm_qwen_service_name: llama-server-qwen
|
||||||
|
llm_qwen_port: 8002
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
|
||||||
|
# =======================================================================
|
||||||
|
# PHASE 1 — Stop and disable llama-server-qwen (bare single-model)
|
||||||
|
# Preserve unit file on disk — rollback target per existing role pattern.
|
||||||
|
# =======================================================================
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Confirm llama-server-qwen current state"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-qwen
|
||||||
|
register: cutover_qwen_status
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Report current llama-server-qwen status"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: >-
|
||||||
|
llama-server-qwen: ActiveState={{ cutover_qwen_status.status.ActiveState | default('unknown') }},
|
||||||
|
UnitFileState={{ cutover_qwen_status.status.UnitFileState | default('unknown') }}.
|
||||||
|
Will stop + disable. Unit file preserved at /etc/systemd/system/llama-server-qwen.service as rollback target.
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Stop llama-server-qwen (:8002, bare single-model)"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-qwen
|
||||||
|
state: stopped
|
||||||
|
register: cutover_qwen_stopped
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Disable llama-server-qwen (prevent auto-start on reboot)"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-qwen
|
||||||
|
enabled: false
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Wait 5s for VRAM to be released"
|
||||||
|
ansible.builtin.pause:
|
||||||
|
seconds: 5
|
||||||
|
when: cutover_qwen_stopped.changed | default(false)
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Verify port 8002 is now free"
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: ss -ltnp
|
||||||
|
register: cutover_port_check
|
||||||
|
changed_when: false
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Fail if port 8002 is still bound"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
Port 8002 is still bound after stopping llama-server-qwen.
|
||||||
|
Check 'ss -ltnp | grep :8002' and resolve before the router can bind.
|
||||||
|
when:
|
||||||
|
- "':8002 ' in (cutover_port_check.stdout | default('')) or ':8002:' in (cutover_port_check.stdout | default(''))"
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Report VRAM state (should be empty)"
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: nvidia-smi --query-compute-apps=pid,name,used_memory --format=csv,noheader
|
||||||
|
register: cutover_vram_free_check
|
||||||
|
changed_when: false
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 1: Print VRAM state"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: >-
|
||||||
|
VRAM after stopping llama-server-qwen:
|
||||||
|
{{ cutover_vram_free_check.stdout if (cutover_vram_free_check.stdout | length > 0)
|
||||||
|
else '(no GPU processes — VRAM free)' }}
|
||||||
|
tags: [cutover_stop_qwen, cutover]
|
||||||
|
|
||||||
|
# =======================================================================
|
||||||
|
# PHASE 2 — Redeploy llama-server-router unit with --port 8002
|
||||||
|
# =======================================================================
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 2: Deploy llama-server-router unit file (port 8002 — production)"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router.service.j2"
|
||||||
|
dest: /etc/systemd/system/llama-server-router.service
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: cutover_router_unit_deployed
|
||||||
|
notify:
|
||||||
|
- reload systemd
|
||||||
|
tags: [cutover_deploy_unit, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 2: Flush handlers (daemon-reload before start)"
|
||||||
|
ansible.builtin.meta: flush_handlers
|
||||||
|
tags: [cutover_deploy_unit, cutover]
|
||||||
|
|
||||||
|
# =======================================================================
|
||||||
|
# PHASE 3 — Enable + start llama-server-router on :8002
|
||||||
|
# =======================================================================
|
||||||
|
|
||||||
|
- name: "[cutover] PHASE 3: Enable + start llama-server-router (production, :8002)"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-router
|
||||||
|
state: "{{ 'restarted' if (cutover_router_unit_deployed.changed | default(false)) else 'started' }}"
|
||||||
|
enabled: true
|
||||||
|
daemon_reload: true
|
||||||
|
tags: [cutover_start_router, cutover]
|
||||||
|
|
||||||
|
# =======================================================================
|
||||||
|
# PHASE 4 — Validation gates 1-3 (hard gates against now-production :8002)
|
||||||
|
# =======================================================================
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1a: Wait for router /health on :8002 (up to 5min — cold model load)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/health"
|
||||||
|
status_code: 200
|
||||||
|
register: cutover_health
|
||||||
|
retries: 30
|
||||||
|
delay: 10
|
||||||
|
until: cutover_health.status == 200
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1a: Trigger model load (router lazy-loads on first request)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/chat/completions"
|
||||||
|
method: POST
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "{{ llm_router_expected_model_id }}"
|
||||||
|
messages:
|
||||||
|
- role: user
|
||||||
|
content: "Reply with one word: hello"
|
||||||
|
max_tokens: 5
|
||||||
|
temperature: 0.0
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 300
|
||||||
|
register: cutover_warmup
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1a: Report warmup"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "Model loaded. finish_reason={{ cutover_warmup.json.choices[0].finish_reason | default('unknown') }}"
|
||||||
|
- "Response: {{ cutover_warmup.json.choices[0].message.content | default('(empty)') | truncate(100) }}"
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1b: Query /v1/models on :8002"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/models"
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
register: cutover_models
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1b: Fail if expected model ID not found"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
GATE 1 FAIL: '{{ llm_router_expected_model_id }}' not found in /v1/models.
|
||||||
|
Returned: {{ cutover_models.json.data | map(attribute='id') | list }}
|
||||||
|
when:
|
||||||
|
- cutover_models.json.data | selectattr('id', 'equalto', llm_router_expected_model_id) | list | length == 0
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1b: Extract ctx-size from router model args"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
cutover_qwen_n_ctx: >-
|
||||||
|
{%- set model = cutover_models.json.data | selectattr('id', 'equalto', llm_router_expected_model_id) | first -%}
|
||||||
|
{%- set args = model.status.args -%}
|
||||||
|
{%- set ctx_idx = args.index('--ctx-size') if '--ctx-size' in args else -1 -%}
|
||||||
|
{{ args[ctx_idx + 1] | int if ctx_idx >= 0 else 0 }}
|
||||||
|
when:
|
||||||
|
- cutover_models.json.data | selectattr('id', 'equalto', llm_router_expected_model_id) | list | length > 0
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1b: Fail if n_ctx < 64000"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "GATE 1 FAIL: --ctx-size={{ cutover_qwen_n_ctx }} < 64000 (Hermes 64K floor)."
|
||||||
|
when:
|
||||||
|
- cutover_qwen_n_ctx is defined
|
||||||
|
- cutover_qwen_n_ctx | int < 64000
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 1b: PASS — n_ctx >= 64K"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "GATE 1 PASS: --ctx-size={{ cutover_qwen_n_ctx }} >= 64000."
|
||||||
|
when:
|
||||||
|
- cutover_qwen_n_ctx is defined
|
||||||
|
- cutover_qwen_n_ctx | int >= 64000
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
# --- Gate 2: Tool-calling through router proxy ---
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 2: Tool-calling probe"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/chat/completions"
|
||||||
|
method: POST
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "{{ llm_router_expected_model_id }}"
|
||||||
|
messages:
|
||||||
|
- role: user
|
||||||
|
content: "What is the current weather in Chicago? Use the provided tool."
|
||||||
|
tools:
|
||||||
|
- type: function
|
||||||
|
function:
|
||||||
|
name: get_weather
|
||||||
|
description: "Get current weather conditions for a city"
|
||||||
|
parameters:
|
||||||
|
type: object
|
||||||
|
properties:
|
||||||
|
city:
|
||||||
|
type: string
|
||||||
|
description: "The city name"
|
||||||
|
required:
|
||||||
|
- city
|
||||||
|
temperature: 0.0
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 120
|
||||||
|
register: cutover_toolcall_probe
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 2: Fail if not finish_reason=tool_calls"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
GATE 2 FAIL: finish_reason={{ cutover_toolcall_probe.json.choices[0].finish_reason | default('(missing)') }}
|
||||||
|
(expected tool_calls). Response: {{ cutover_toolcall_probe.json | to_json }}
|
||||||
|
when:
|
||||||
|
- cutover_toolcall_probe.json.choices[0].finish_reason | default('') != 'tool_calls'
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 2: PASS"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "GATE 2 PASS: finish_reason=tool_calls"
|
||||||
|
- "function: {{ cutover_toolcall_probe.json.choices[0].message.tool_calls[0].function.name | default('(unknown)') }}"
|
||||||
|
- "arguments: {{ cutover_toolcall_probe.json.choices[0].message.tool_calls[0].function.arguments | default('(none)') }}"
|
||||||
|
when:
|
||||||
|
- cutover_toolcall_probe.json.choices[0].finish_reason | default('') == 'tool_calls'
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
# --- Gate 2b: Hallucination stress ---
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 2b: Hallucination stress probe"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/chat/completions"
|
||||||
|
method: POST
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "{{ llm_router_expected_model_id }}"
|
||||||
|
messages:
|
||||||
|
- role: user
|
||||||
|
content: "Tell me a brief fact about the planet Mars. Do not call any functions."
|
||||||
|
tools:
|
||||||
|
- type: function
|
||||||
|
function:
|
||||||
|
name: get_weather
|
||||||
|
description: "Get current weather conditions for a city"
|
||||||
|
parameters:
|
||||||
|
type: object
|
||||||
|
properties:
|
||||||
|
city:
|
||||||
|
type: string
|
||||||
|
required:
|
||||||
|
- city
|
||||||
|
temperature: 0.1
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 120
|
||||||
|
register: cutover_halluc_probe
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 2b: Fail if spurious tool_calls"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
GATE 2b FAIL: finish_reason=tool_calls on unrelated prompt (Mars fact).
|
||||||
|
Over-triggering through router. Response: {{ cutover_halluc_probe.json | to_json }}
|
||||||
|
when:
|
||||||
|
- cutover_halluc_probe.json.choices[0].finish_reason | default('') == 'tool_calls'
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 2b: PASS"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "GATE 2b PASS: finish_reason={{ cutover_halluc_probe.json.choices[0].finish_reason }} — no spurious tool_calls."
|
||||||
|
when:
|
||||||
|
- cutover_halluc_probe.json.choices[0].finish_reason | default('') != 'tool_calls'
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
# --- Gate 3: VRAM guard ---
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 3: Check VRAM usage (--models-max 1 guard)"
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: nvidia-smi --query-gpu=memory.used,memory.total,utilization.gpu --format=csv,noheader
|
||||||
|
register: cutover_vram_post
|
||||||
|
changed_when: false
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 3: Parse VRAM used MiB"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
cutover_vram_used_mib: "{{ cutover_vram_post.stdout.split(',')[0].strip().split(' ')[0] | int }}"
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 3: Fail if VRAM exceeds ceiling"
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
GATE 3 FAIL: {{ cutover_vram_used_mib }} MiB > {{ llm_router_vram_max_mib }} MiB ceiling.
|
||||||
|
Full: {{ cutover_vram_post.stdout }}
|
||||||
|
when:
|
||||||
|
- cutover_vram_used_mib | int > llm_router_vram_max_mib | int
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 3: Count GPU processes"
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: nvidia-smi --query-compute-apps=pid,name --format=csv,noheader
|
||||||
|
register: cutover_gpu_procs
|
||||||
|
changed_when: false
|
||||||
|
failed_when: false
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 3: PASS"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "GATE 3 PASS: {{ cutover_vram_used_mib }} MiB / {{ llm_router_vram_max_mib }} MiB ceiling."
|
||||||
|
- "GPU processes: {{ cutover_gpu_procs.stdout_lines | default(['(none)']) }}"
|
||||||
|
- "Full nvidia-smi: {{ cutover_vram_post.stdout }}"
|
||||||
|
when:
|
||||||
|
- cutover_vram_used_mib | int <= llm_router_vram_max_mib | int
|
||||||
|
tags: [cutover_validate, cutover]
|
||||||
|
|
||||||
|
# =======================================================================
|
||||||
|
# PHASE 5 — Gate 4: Bundled SvelteKit Web UI (required this time)
|
||||||
|
# =======================================================================
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 4: Check bundled SvelteKit UI at :8002"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/"
|
||||||
|
status_code: [200, 301, 302]
|
||||||
|
return_content: true
|
||||||
|
timeout: 30
|
||||||
|
register: cutover_ui_check
|
||||||
|
failed_when: false
|
||||||
|
tags: [cutover_validate, cutover_ui, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 4: Inspect UI content"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
cutover_ui_is_html: "{{ 'html' in (cutover_ui_check.content | default('') | lower) or '<!doctype' in (cutover_ui_check.content | default('') | lower) }}"
|
||||||
|
cutover_ui_has_model_select: "{{ 'select' in (cutover_ui_check.content | default('') | lower) or 'model' in (cutover_ui_check.content | default('') | lower) }}"
|
||||||
|
when: cutover_ui_check is defined
|
||||||
|
tags: [cutover_validate, cutover_ui, cutover]
|
||||||
|
|
||||||
|
- name: "[cutover] GATE 4: Report UI check and bookmark URL"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "======================================================================"
|
||||||
|
- "GATE 4 UI CHECK:"
|
||||||
|
- " HTTP status: {{ cutover_ui_check.status | default('UNREACHABLE') }}"
|
||||||
|
- " Is HTML: {{ cutover_ui_is_html | default(false) }}"
|
||||||
|
- " Contains model/select: {{ cutover_ui_has_model_select | default(false) }}"
|
||||||
|
- " BOOKMARK URL: http://{{ llm_router_bind_address }}:{{ llm_router_port }}/"
|
||||||
|
- " {{ 'GATE 4 PASS — UI serving HTML at :8002.' if (cutover_ui_check.status | default(0) | int in [200, 301, 302]) else 'GATE 4 WARN — UI not reachable (HTTP ' + (cutover_ui_check.status | default('FAIL') | string) + ').' }}"
|
||||||
|
- "======================================================================"
|
||||||
|
when: cutover_ui_check is defined
|
||||||
|
tags: [cutover_validate, cutover_ui, cutover]
|
||||||
|
|
||||||
|
# =======================================================================
|
||||||
|
# CUTOVER SUMMARY
|
||||||
|
# =======================================================================
|
||||||
|
|
||||||
|
- name: "[cutover] CUTOVER SUMMARY — production promoted"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "======================================================================"
|
||||||
|
- "CUTOVER COMPLETE: llama-server-router is now production."
|
||||||
|
- ""
|
||||||
|
- " Service: llama-server-router.service (enabled, running)"
|
||||||
|
- " Port: 8002 (unchanged for all 8 Hermes profiles)"
|
||||||
|
- " Model: {{ llm_router_expected_model_id }}"
|
||||||
|
- " Mode: Router/supervisor (--models-dir /opt/models, --models-max 1)"
|
||||||
|
- ""
|
||||||
|
- " Gate 1 (n_ctx >= 64K): PASS ({{ cutover_qwen_n_ctx | default('N/A') }})"
|
||||||
|
- " Gate 2 (tool-calling): PASS (finish_reason=tool_calls)"
|
||||||
|
- " Gate 2b (halluc stress): PASS (no spurious tool_calls)"
|
||||||
|
- " Gate 3 (VRAM <= 23000MiB): PASS ({{ cutover_vram_used_mib | default('N/A') }} MiB)"
|
||||||
|
- " Gate 4 (Web UI): HTTP {{ cutover_ui_check.status | default('N/A') }}"
|
||||||
|
- ""
|
||||||
|
- " ROLLBACK TARGET: /etc/systemd/system/llama-server-qwen.service (unit preserved)"
|
||||||
|
- " ROLLBACK CMD: sudo systemctl enable --now llama-server-qwen"
|
||||||
|
- " sudo systemctl disable --now llama-server-router"
|
||||||
|
- " Or: ansible-playbook -i inventory.yml day2_cutover_qwen_to_router.yml --tags cutover_rollback"
|
||||||
|
- ""
|
||||||
|
- " Web UI bookmark: http://{{ llm_router_bind_address }}:{{ llm_router_port }}/"
|
||||||
|
- "======================================================================"
|
||||||
|
tags: [cutover]
|
||||||
|
|
||||||
|
# =======================================================================
|
||||||
|
# ROLLBACK — tag cutover_rollback reverses the cutover
|
||||||
|
# Run: ansible-playbook -i inventory.yml day2_cutover_qwen_to_router.yml --tags cutover_rollback
|
||||||
|
# WARNING: rollback_task has no dependency on cutover tags — safe to run standalone.
|
||||||
|
# =======================================================================
|
||||||
|
|
||||||
|
- name: "[cutover_rollback] Stop + disable llama-server-router"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-router
|
||||||
|
state: stopped
|
||||||
|
enabled: false
|
||||||
|
tags: [cutover_rollback, never] # 'never' = only runs with explicit --tags cutover_rollback
|
||||||
|
|
||||||
|
- name: "[cutover_rollback] Enable + start llama-server-qwen (restore bare :8002)"
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-qwen
|
||||||
|
state: started
|
||||||
|
enabled: true
|
||||||
|
tags: [cutover_rollback, never]
|
||||||
|
|
||||||
|
- name: "[cutover_rollback] Verify rollback /health"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_bind_address | default('10.1.71.130') }}:8002/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
register: cutover_rollback_health
|
||||||
|
failed_when: false
|
||||||
|
tags: [cutover_rollback, never]
|
||||||
|
|
||||||
|
- name: "[cutover_rollback] Report rollback result"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: >-
|
||||||
|
ROLLBACK: llama-server-qwen :8002 health returned
|
||||||
|
{{ cutover_rollback_health.status | default('UNREACHABLE') }}.
|
||||||
|
{{ 'OK — production restored to bare qwen.' if (cutover_rollback_health.status | default(0) | int == 200)
|
||||||
|
else 'WARNING — health check failed. Check manually.' }}
|
||||||
|
tags: [cutover_rollback, never]
|
||||||
|
|
||||||
|
handlers:
|
||||||
|
- name: reload systemd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
daemon_reload: true
|
||||||
@@ -0,0 +1,277 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: playbooks/day2_per_model_ctx_size.yml
|
||||||
|
# DESCRIPTION: Right-size --ctx-size per model workload on llama-server-router
|
||||||
|
# (already in --models-preset mode since t_9adf0889).
|
||||||
|
#
|
||||||
|
# Context (t_ryan_per_model_ctx, 2026-08-13, requested by Ryan via JARVIS):
|
||||||
|
# All 3 preset models currently launch with a uniform --ctx-size 65536.
|
||||||
|
# This playbook narrows two of them to match actual workload:
|
||||||
|
# - Meta-Llama-3.1-8B-Instruct-Q4_K_M (alias Meta-Llama-3.1-8B-Instruct-4bit):
|
||||||
|
# ctx-size 65536 -> 8192 (tool-routing / micro-tasks: title gen, MCP
|
||||||
|
# tool calls, approval checks)
|
||||||
|
# - Phi-3.5-mini-instruct-Q8_0 (alias Phi-3.5-mini-instruct-8bit):
|
||||||
|
# ctx-size 65536 -> 32768 (long web scrapes / session-log compression)
|
||||||
|
# Both also move flash-attn from "auto" to explicit "true" per Ryan's spec.
|
||||||
|
# Qwen3.6-35B-A3B-UD-Q4_K_S is INTENTIONALLY left untouched at 65536/auto.
|
||||||
|
#
|
||||||
|
# Existing aliases (Meta-Llama-3.1-8B-Instruct-4bit, Phi-3.5-mini-instruct-8bit)
|
||||||
|
# are PRESERVED as-is. Ryan's pasted TOML used different alias strings
|
||||||
|
# ("llama-3.1-8b", "phi-3.5-mini") but renaming aliases was not explicitly
|
||||||
|
# requested and would break live Hermes custom_providers routing — flagged
|
||||||
|
# in the deployment report rather than applied silently.
|
||||||
|
#
|
||||||
|
# IMPORTANT — Hermes side effect: /home/hermes/.hermes/config.yaml declares
|
||||||
|
# context_length: 65536 for both these models under custom_providers. This
|
||||||
|
# playbook does NOT touch that file (out of role/agent scope) but the value
|
||||||
|
# becomes STALE the moment this playbook lands. Flag to JARVIS/Maria Hill.
|
||||||
|
#
|
||||||
|
# Usage (from ~/git/homelab/ansible):
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day2_per_model_ctx_size.yml
|
||||||
|
#
|
||||||
|
# Author: War Machine (2026-08-13, t_ryan_per_model_ctx)
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Right-size per-model ctx-size on llama-server-router (Llama 8k, Phi 32k)"
|
||||||
|
hosts: astro_orbiter
|
||||||
|
gather_facts: false
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# Preset mode already active in production (t_9adf0889) — keep it on.
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
llm_router_preset_path: /opt/llama-server-router-preset.ini
|
||||||
|
llm_router_enabled: true
|
||||||
|
|
||||||
|
# Production port
|
||||||
|
llm_router_port: 8002
|
||||||
|
llm_router_bind_address: "10.1.71.130"
|
||||||
|
llm_router_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
llm_bind_address: "10.1.71.130"
|
||||||
|
llm_allowed_source_cidr: "10.1.70.0/24"
|
||||||
|
|
||||||
|
llm_service_user: jarvis
|
||||||
|
llm_binary_path: /opt/llama.cpp/build/bin/llama-server
|
||||||
|
llm_models_dir: /opt/models
|
||||||
|
llm_router_service_name: llama-server-router
|
||||||
|
llm_router_models_dir: /opt/models
|
||||||
|
llm_router_models_max: 4
|
||||||
|
llm_router_parallel: 1
|
||||||
|
llm_router_gpu_layers: 99
|
||||||
|
llm_router_batch_size: 2048
|
||||||
|
llm_router_ubatch_size: 512
|
||||||
|
llm_router_cache_type_k: q4_0
|
||||||
|
llm_router_cache_type_v: q4_0
|
||||||
|
|
||||||
|
# Qwen — untouched baseline (also used as router-wide fallback default)
|
||||||
|
llm_router_ctx_size: 65536
|
||||||
|
llm_router_flash_attn: "auto"
|
||||||
|
llm_router_expected_model_id: "Qwen3.6-35B-A3B-UD-Q4_K_S"
|
||||||
|
llm_router_vram_max_mib: 23000
|
||||||
|
|
||||||
|
# --- THE CHANGE: per-model overrides ---
|
||||||
|
llm_router_llama_ctx_size: 8192
|
||||||
|
llm_router_llama_flash_attn: "true"
|
||||||
|
llm_router_phi_ctx_size: 32768
|
||||||
|
llm_router_phi_flash_attn: "true"
|
||||||
|
|
||||||
|
handlers:
|
||||||
|
- name: reload systemd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
daemon_reload: true
|
||||||
|
become: true
|
||||||
|
listen: "reload systemd"
|
||||||
|
|
||||||
|
- name: restart router
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: llama-server-router
|
||||||
|
state: restarted
|
||||||
|
become: true
|
||||||
|
listen: "restart router"
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 1: Deploy the preset INI with new per-model ctx-size/flash-attn
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Deploy preset INI to {{ llm_router_preset_path }}"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2"
|
||||||
|
dest: "{{ llm_router_preset_path }}"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: ctx_resize_preset_deployed
|
||||||
|
notify:
|
||||||
|
- restart router
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Deploy router systemd unit (drop global --ctx-size/--flash-attn in preset mode)"
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: "../roles/llm-inference-multimodel/templates/llama-server-router.service.j2"
|
||||||
|
dest: /etc/systemd/system/llama-server-router.service
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
register: ctx_resize_unit_deployed
|
||||||
|
notify:
|
||||||
|
- reload systemd
|
||||||
|
- restart router
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Flush handlers (daemon-reload + router restart if changed)"
|
||||||
|
ansible.builtin.meta: flush_handlers
|
||||||
|
|
||||||
|
# ==========================================================================
|
||||||
|
# PHASE 2: Verify
|
||||||
|
# ==========================================================================
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Wait for /health"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 30
|
||||||
|
retries: 12
|
||||||
|
delay: 5
|
||||||
|
register: ctx_resize_health
|
||||||
|
until: ctx_resize_health.status == 200
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Query /v1/models"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/models"
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 30
|
||||||
|
register: ctx_resize_models
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Trigger load — Llama (confirms actual load + captures live args)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/chat/completions"
|
||||||
|
method: POST
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "Meta-Llama-3.1-8B-Instruct-Q4_K_M"
|
||||||
|
messages:
|
||||||
|
- role: user
|
||||||
|
content: "Reply with one word: hello"
|
||||||
|
max_tokens: 5
|
||||||
|
temperature: 0.0
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 120
|
||||||
|
register: ctx_resize_llama_warmup
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Trigger load — Phi (confirms actual load + captures live args)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/chat/completions"
|
||||||
|
method: POST
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "Phi-3.5-mini-instruct-Q8_0"
|
||||||
|
messages:
|
||||||
|
- role: user
|
||||||
|
content: "Reply with one word: hello"
|
||||||
|
max_tokens: 5
|
||||||
|
temperature: 0.0
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 120
|
||||||
|
register: ctx_resize_phi_warmup
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Re-query /v1/models after warmup (final state)"
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://{{ llm_router_bind_address }}:{{ llm_router_port }}/v1/models"
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
timeout: 30
|
||||||
|
register: ctx_resize_models_final
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Extract Llama args"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
ctx_resize_llama_args: >-
|
||||||
|
{{ (ctx_resize_models_final.json.data | selectattr('id', 'equalto', 'Meta-Llama-3.1-8B-Instruct-Q4_K_M') | first).status.args }}
|
||||||
|
ctx_resize_llama_status: >-
|
||||||
|
{{ (ctx_resize_models_final.json.data | selectattr('id', 'equalto', 'Meta-Llama-3.1-8B-Instruct-Q4_K_M') | first).status.value }}
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Extract Phi args"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
ctx_resize_phi_args: >-
|
||||||
|
{{ (ctx_resize_models_final.json.data | selectattr('id', 'equalto', 'Phi-3.5-mini-instruct-Q8_0') | first).status.args }}
|
||||||
|
ctx_resize_phi_status: >-
|
||||||
|
{{ (ctx_resize_models_final.json.data | selectattr('id', 'equalto', 'Phi-3.5-mini-instruct-Q8_0') | first).status.value }}
|
||||||
|
|
||||||
|
- name: "[ctx-resize] Extract Qwen args (must be unchanged)"
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
ctx_resize_qwen_args: >-
|
||||||
|
{{ (ctx_resize_models_final.json.data | selectattr('id', 'equalto', 'Qwen3.6-35B-A3B-UD-Q4_K_S') | first).status.args }}
|
||||||
|
|
||||||
|
- name: "[ctx-resize] GATE — Llama ctx-size must be 8192"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- "'8192' in ctx_resize_llama_args"
|
||||||
|
- ctx_resize_llama_args[ctx_resize_llama_args.index('--ctx-size') + 1] == '8192'
|
||||||
|
fail_msg: "Llama ctx-size not 8192. Args: {{ ctx_resize_llama_args }}"
|
||||||
|
success_msg: "Llama ctx-size confirmed 8192."
|
||||||
|
|
||||||
|
- name: "[ctx-resize] GATE — Llama flash-attn must be true"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ctx_resize_llama_args[ctx_resize_llama_args.index('--flash-attn') + 1] == 'true'
|
||||||
|
fail_msg: "Llama flash-attn not true. Args: {{ ctx_resize_llama_args }}"
|
||||||
|
success_msg: "Llama flash-attn confirmed true."
|
||||||
|
|
||||||
|
- name: "[ctx-resize] GATE — Llama loaded successfully"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ctx_resize_llama_status == 'loaded'
|
||||||
|
fail_msg: "Llama status is '{{ ctx_resize_llama_status }}', expected 'loaded'."
|
||||||
|
success_msg: "Llama status confirmed 'loaded'."
|
||||||
|
|
||||||
|
- name: "[ctx-resize] GATE — Phi ctx-size must be 32768"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ctx_resize_phi_args[ctx_resize_phi_args.index('--ctx-size') + 1] == '32768'
|
||||||
|
fail_msg: "Phi ctx-size not 32768. Args: {{ ctx_resize_phi_args }}"
|
||||||
|
success_msg: "Phi ctx-size confirmed 32768."
|
||||||
|
|
||||||
|
- name: "[ctx-resize] GATE — Phi flash-attn must be true"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ctx_resize_phi_args[ctx_resize_phi_args.index('--flash-attn') + 1] == 'true'
|
||||||
|
fail_msg: "Phi flash-attn not true. Args: {{ ctx_resize_phi_args }}"
|
||||||
|
success_msg: "Phi flash-attn confirmed true."
|
||||||
|
|
||||||
|
- name: "[ctx-resize] GATE — Phi loaded successfully"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ctx_resize_phi_status == 'loaded'
|
||||||
|
fail_msg: "Phi status is '{{ ctx_resize_phi_status }}', expected 'loaded'."
|
||||||
|
success_msg: "Phi status confirmed 'loaded'."
|
||||||
|
|
||||||
|
- name: "[ctx-resize] GATE — Qwen ctx-size UNCHANGED at 65536"
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ctx_resize_qwen_args[ctx_resize_qwen_args.index('--ctx-size') + 1] == '65536'
|
||||||
|
fail_msg: "Qwen ctx-size changed unexpectedly! Args: {{ ctx_resize_qwen_args }}"
|
||||||
|
success_msg: "Qwen ctx-size confirmed UNCHANGED at 65536."
|
||||||
|
|
||||||
|
- name: "[ctx-resize] PASS — summary"
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg:
|
||||||
|
- "================================================================"
|
||||||
|
- "PER-MODEL CTX-SIZE DEPLOYMENT — COMPLETE"
|
||||||
|
- ""
|
||||||
|
- " Llama-3.1-8B (Meta-Llama-3.1-8B-Instruct-Q4_K_M):"
|
||||||
|
- " status: {{ ctx_resize_llama_status }}"
|
||||||
|
- " args: {{ ctx_resize_llama_args }}"
|
||||||
|
- ""
|
||||||
|
- " Phi-3.5-mini (Phi-3.5-mini-instruct-Q8_0):"
|
||||||
|
- " status: {{ ctx_resize_phi_status }}"
|
||||||
|
- " args: {{ ctx_resize_phi_args }}"
|
||||||
|
- ""
|
||||||
|
- " Qwen3.6-35B-A3B-UD-Q4_K_S: UNCHANGED (ctx-size 65536, args: {{ ctx_resize_qwen_args }})"
|
||||||
|
- ""
|
||||||
|
- " ACTION NEEDED: /home/hermes/.hermes/config.yaml custom_providers"
|
||||||
|
- " context_length: 65536 for both Meta-Llama-3.1-8B-Instruct-4bit and"
|
||||||
|
- " Phi-3.5-mini-instruct-8bit is now STALE (actual: 8192 / 32768)."
|
||||||
|
- " Flag to JARVIS/Maria Hill for correction — NOT done by this playbook."
|
||||||
|
- "================================================================"
|
||||||
@@ -0,0 +1,38 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# Playbook: day2_qwen38_ctx128k.yml
|
||||||
|
# Purpose: Bump Qwen3.8-27B-Q4_K_M ctx-size from 32768 to 131072 (128K)
|
||||||
|
# on astro-orbiter's production router (port 8002).
|
||||||
|
#
|
||||||
|
# What this playbook does:
|
||||||
|
# 1. Renders the updated llama-server-router-preset.ini.j2 (now with
|
||||||
|
# llm_router_qwen38_ctx_size: 131072) to /opt/llama-server-router-preset.ini.
|
||||||
|
# 2. Restarts llama-server-router.service.
|
||||||
|
# 3. Verifies the router loads Qwen3.8-27B at ctx=131072 in status.args.
|
||||||
|
#
|
||||||
|
# Context:
|
||||||
|
# - Empirical VRAM test (t_4455a44c): 131072 ctx = 20,282 MiB Qwen3.8
|
||||||
|
# + 558 MiB nomic-embed = ~20.8GB total; ~3.2GB headroom on 24GB RTX 3090.
|
||||||
|
# Co-resident with nomic-embed: comfortably fits.
|
||||||
|
# - Ryan approved this deployment.
|
||||||
|
# - Semaphore SSH gap for astro-orbiter still applies (t_730f9584 / t_33acbb2e);
|
||||||
|
# running direct CLI Ansible per standing exception.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# cd /home/hermes/git/homelab/ansible
|
||||||
|
# env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook \
|
||||||
|
# -i inventory.yml \
|
||||||
|
# playbooks/day2_qwen38_ctx128k.yml
|
||||||
|
#
|
||||||
|
# Task reference: t_441470b9 — War Machine, 2026-08-16
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
- name: Bump Qwen3.8-27B ctx-size to 131072 on astro-orbiter
|
||||||
|
hosts: astro-orbiter
|
||||||
|
become: true
|
||||||
|
vars:
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
llm_router_qwen38_ctx_size: 131072
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference-multimodel
|
||||||
|
tags: [preset, systemd, verify]
|
||||||
@@ -0,0 +1,65 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# Playbook: day2_qwen38_ctx128k_rollback.yml
|
||||||
|
# Purpose: Roll back Qwen3.8-27B-Q4_K_M ctx-size from 131072 back to 65536
|
||||||
|
# on astro-orbiter's production router (port 8002).
|
||||||
|
#
|
||||||
|
# What this playbook does:
|
||||||
|
# 1. Renders the updated llama-server-router-preset.ini.j2 (now with
|
||||||
|
# llm_router_qwen38_ctx_size: 65536) to
|
||||||
|
# /opt/llama-server-router-preset.ini.
|
||||||
|
# 2. Restarts llama-server-router.service.
|
||||||
|
# 3. Verifies the router loads Qwen3.8-27B at ctx=65536 in status.args.
|
||||||
|
#
|
||||||
|
# Context:
|
||||||
|
# - t_441470b9 (2026-08-16): ctx-size bumped 32768 -> 131072. Verified VRAM
|
||||||
|
# at 131072 ctx with only Qwen3.8 + nomic-embed co-resident: ~20,282 MiB
|
||||||
|
# + 558 MiB = ~20.8 GB on 24 GB RTX 3090. Comfortably safe.
|
||||||
|
# - t_72646029 (2026-08-17): Phi-3.5mini moved to GPU (n-gpu-layers=99)
|
||||||
|
# to enable concurrent residency with CPU-offloaded Coder-14B and
|
||||||
|
# Llama-3.1-8B. This added ~2GB CUDA context buffers for Phi + shifted
|
||||||
|
# Phi's model weights onto the GPU (~3.8GB).
|
||||||
|
# - NEW steady-state VRAM: Qwen3.8 @ 131072 ctx (~20,282 MiB) + nomic-embed
|
||||||
|
# (~558 MiB) + Llama CUDA ctx (~1,706 MiB) + Coder CUDA ctx (~1,390 MiB)
|
||||||
|
# = ~24,004 MiB. Adding Phi-3.5 (~3,800 MiB weights + ~1.4 GB CUDA ctx)
|
||||||
|
# pushes total to ~29,000+ MiB — exceeding the 24,576 MiB RTX 3090 limit.
|
||||||
|
# Qwen3.8-27B-131072 now fails to load (HTTP 500, OOM before llama.cpp
|
||||||
|
# reaches the model-loading phase).
|
||||||
|
# - FIX: reduce Qwen3.8 ctx-size 131072 -> 65536. This reduces KV cache
|
||||||
|
# from ~6GB to ~3GB, freeing ~3GB of VRAM. New estimated steady-state:
|
||||||
|
# Qwen3.8 @ 65536 ctx (~17,068 MiB) + nomic (~558) + Llama ctx (~1,706)
|
||||||
|
# + Coder ctx (~1,390) + Phi-3.5 (~3,800 + ~1,400 CUDA ctx) = ~25,922 MiB.
|
||||||
|
# Still over 24,576 — see "Phase 2" below for the secondary fix.
|
||||||
|
#
|
||||||
|
# IMPORTANT: Rolling back ctx-size alone may NOT be sufficient. The
|
||||||
|
# hardware reference (astro-orbiter-hardware.md line 166, t_72646029)
|
||||||
|
# states steady-state ~24,004 MiB WITHOUT Phi on GPU. Adding Phi-3.5 back
|
||||||
|
# to GPU tips it over. This playbook handles the context rollback; if Qwen3.8
|
||||||
|
# still fails to load after Phase R, Wong should escalate to Ryan for a
|
||||||
|
# decision on either (a) offloading Phi-3.5mini to CPU (n-gpu-layers=0),
|
||||||
|
# or (b) adding a second GPU. Document the Phase 2 finding as a separate
|
||||||
|
# follow-up task if needed.
|
||||||
|
#
|
||||||
|
# The 64K floor from the 2026-08-12 cutover validation (t_cd0d5388, Gate 1)
|
||||||
|
# still applies — ctx-size=65536 satisfies it.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# cd /home/hermes/git/homelab/ansible
|
||||||
|
# env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook \
|
||||||
|
# -i inventory.yml \
|
||||||
|
# playbooks/day2_qwen38_ctx128k_rollback.yml
|
||||||
|
#
|
||||||
|
# Task reference: t_c9fed26c — War Machine benchmark, 2026-08-18
|
||||||
|
# Root cause: t_72646029 CPU-offload deployment added Phi-3.5 to GPU,
|
||||||
|
# shifting total VRAM past the 24,576 MiB ceiling when Qwen3.8 runs at 128K.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
- name: Roll back Qwen3.8-27B ctx-size to 65536 on astro-orbiter
|
||||||
|
hosts: astro-orbiter
|
||||||
|
become: true
|
||||||
|
vars:
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
llm_router_qwen38_ctx_size: 65536
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference-multimodel
|
||||||
|
tags: [preset, systemd, verify]
|
||||||
@@ -0,0 +1,36 @@
|
|||||||
|
---
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# Playbook: day2_swap_qwen38.yml
|
||||||
|
# Purpose: Swap the primary production model on astro-orbiter router from
|
||||||
|
# Qwen3.6-35B-A3B-UD-Q4_K_S to Qwen3.8-27B-Q4_K_M.
|
||||||
|
# This is a GitOps-encoded record of the swap performed 2026-08-16
|
||||||
|
# per Ryan's direction (kanban task t_f5f7e9ad).
|
||||||
|
#
|
||||||
|
# What this playbook does:
|
||||||
|
# 1. Renders the updated llama-server-router-preset.ini.j2 to
|
||||||
|
# /opt/llama-server-router-preset.ini on astro-orbiter.
|
||||||
|
# 2. Reloads the llama-server-router service (SIGHUP / restart as needed).
|
||||||
|
# 3. Verifies the new model ID appears in /v1/models.
|
||||||
|
#
|
||||||
|
# Prerequisites:
|
||||||
|
# - Qwen3.8-27B-Q4_K_M.gguf must be present in /opt/models on astro-orbiter.
|
||||||
|
# (Downloaded out-of-band via wget during the swap task.)
|
||||||
|
# - roles/llm-inference-multimodel/defaults/main.yml updated to reference
|
||||||
|
# Qwen3.8-27B-Q4_K_M (done in this same commit).
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook \
|
||||||
|
# -i inventory.yml \
|
||||||
|
# playbooks/day2_swap_qwen38.yml
|
||||||
|
#
|
||||||
|
# Task reference: t_f5f7e9ad — War Machine, 2026-08-16
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
- name: Swap primary model to Qwen3.8-27B-Q4_K_M on astro-orbiter
|
||||||
|
hosts: astro-orbiter
|
||||||
|
become: true
|
||||||
|
vars:
|
||||||
|
llm_router_preset_enabled: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference-multimodel
|
||||||
|
tags: [preset, systemd, verify]
|
||||||
@@ -0,0 +1,22 @@
|
|||||||
|
---
|
||||||
|
# Playbook: day3_deploy_qwen38_ctx131k.yml
|
||||||
|
# Purpose: Deploy Qwen3.8-27B-Q4_K_M ctx-size 65536 -> 131072 to astro-orbiter
|
||||||
|
# via llama-swap config re-render + restart.
|
||||||
|
#
|
||||||
|
# The git change to defaults/main.yml (line 235: ctx_size: 131072) is already staged.
|
||||||
|
# This playbook renders /etc/llama-swap/config.yaml from the updated defaults
|
||||||
|
# and restarts llama-swap to load the new ctx-size.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# cd /home/hermes/git/homelab/ansible
|
||||||
|
# ansible-playbook -i inventory.yml playbooks/day3_deploy_qwen38_ctx131k.yml
|
||||||
|
#
|
||||||
|
- name: Deploy Qwen3.8 ctx-size 131072 to astro-orbiter
|
||||||
|
hosts: astro-orbiter
|
||||||
|
become: true
|
||||||
|
vars:
|
||||||
|
llm_swapmode_enabled: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: llm-inference-multimodel
|
||||||
|
tags: [swapmode_config, swapmode_systemd, swapmode_verify]
|
||||||
@@ -0,0 +1,6 @@
|
|||||||
|
---
|
||||||
|
- name: Deploy Multica + Caddy
|
||||||
|
hosts: multica
|
||||||
|
become: true
|
||||||
|
roles:
|
||||||
|
- role: multica_docker
|
||||||
@@ -0,0 +1,82 @@
|
|||||||
|
---
|
||||||
|
- name: Deploy Paperclip stack (behind the shared nginx-proxy)
|
||||||
|
hosts: illuminations
|
||||||
|
become: true
|
||||||
|
vars_files:
|
||||||
|
- "{{ playbook_dir }}/../group_vars/all/vars"
|
||||||
|
- "{{ playbook_dir }}/../group_vars/all/vault"
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- docker-host
|
||||||
|
- nginx-proxy # must come before paperclip-docker (it publishes its vhost through it)
|
||||||
|
- paperclip-docker
|
||||||
|
|
||||||
|
post_tasks:
|
||||||
|
# CLI-based on purpose: community.docker.docker_container_info needs the
|
||||||
|
# Docker SDK for Python, which the paperclip-docker role no longer installs.
|
||||||
|
- name: Verify stack containers are running
|
||||||
|
ansible.builtin.command: "docker inspect -f '{% raw %}{{.State.Running}}{% endraw %}' {{ item }}"
|
||||||
|
register: container_status
|
||||||
|
loop:
|
||||||
|
- paperclip-db
|
||||||
|
- paperclip
|
||||||
|
- nginx
|
||||||
|
- certbot
|
||||||
|
changed_when: false
|
||||||
|
failed_when: container_status.rc != 0 or container_status.stdout | trim != 'true'
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item }}"
|
||||||
|
|
||||||
|
- name: Verify Docker is available
|
||||||
|
ansible.builtin.command: docker --version
|
||||||
|
register: docker_version
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: Show Docker version
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "Docker version: {{ docker_version.stdout }}"
|
||||||
|
|
||||||
|
- name: Verify docker-compose plugin is available
|
||||||
|
ansible.builtin.command: docker compose version
|
||||||
|
register: compose_version
|
||||||
|
changed_when: false
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: Show docker-compose version
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "Docker Compose version: {{ compose_version.stdout | default('docker-compose plugin not found') }}"
|
||||||
|
|
||||||
|
- name: Display deployment summary
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: |
|
||||||
|
Paperclip stack deployed successfully!
|
||||||
|
|
||||||
|
Access points:
|
||||||
|
- HTTPS: https://{{ paperclip_domain }}
|
||||||
|
- HTTP (redirects to HTTPS): http://{{ paperclip_domain }}
|
||||||
|
|
||||||
|
Services:
|
||||||
|
- Paperclip: {{ paperclip_host }}:{{ paperclip_port }}
|
||||||
|
- nginx (shared reverse proxy): 0.0.0.0:443 / 0.0.0.0:80, config in {{ nginx_proxy_conf_dir }}
|
||||||
|
- certbot: Running certificate renewal checks
|
||||||
|
|
||||||
|
Data location:
|
||||||
|
- {{ paperclip_base_path }}/data
|
||||||
|
|
||||||
|
Certificates:
|
||||||
|
- {{ nginx_proxy_certs_dir }}/live/{{ paperclip_domain }}/
|
||||||
|
|
||||||
|
vLLM endpoint:
|
||||||
|
- {{ vllm_endpoint }}
|
||||||
|
|
||||||
|
OpenCode configuration:
|
||||||
|
- Config: {{ paperclip_base_path }}/.config/opencode/opencode.jsonc
|
||||||
|
- Model: Gemma-4-26B (AWQ)
|
||||||
|
- Endpoint: {{ vllm_endpoint }}/v1
|
||||||
|
|
||||||
|
Next steps:
|
||||||
|
1. Verify DNS resolution for {{ paperclip_domain }}
|
||||||
|
2. Visit https://{{ paperclip_domain }} to access Paperclip
|
||||||
|
3. OpenCode should auto-initialize with vLLM at {{ vllm_endpoint }}
|
||||||
|
4. Run day1_deploy_hermes_docker.yml (publishes its dashboard through the same nginx)
|
||||||
|
5. Configure agents and skills
|
||||||
@@ -0,0 +1,11 @@
|
|||||||
|
# install-claude.yml
|
||||||
|
---
|
||||||
|
# Usage: ansible-playbook -i inventory.ini install-claude.yml
|
||||||
|
- name: Install Claude Code on Ubuntu servers
|
||||||
|
hosts: claude_servers
|
||||||
|
become: false # the role escalates only where it needs to
|
||||||
|
roles:
|
||||||
|
- role: claude-code
|
||||||
|
vars:
|
||||||
|
claude_code_install_method: apt # or: native
|
||||||
|
claude_code_apt_channel: stable # or: latest
|
||||||
@@ -0,0 +1,66 @@
|
|||||||
|
---
|
||||||
|
# Example playbook. The role takes multica_pat as a VALUE — pick ONE of the
|
||||||
|
# lookups below (or any other) and delete the rest. Changing secret provider
|
||||||
|
# later is a change to this file only; the role is untouched.
|
||||||
|
- name: Provision Multica agent hosts
|
||||||
|
hosts: multica_agent_hosts
|
||||||
|
become: true
|
||||||
|
|
||||||
|
vars:
|
||||||
|
multica_server_url: "https://multica.wdw-labs.cloud"
|
||||||
|
multica_app_url: "https://multica.wdw-labs.cloud"
|
||||||
|
multica_version: "0.6.5"
|
||||||
|
multica_node_version: "24.22.1"
|
||||||
|
multica_workspaces_root: "/opt/multica/workspaces"
|
||||||
|
# No NAS mount under the workspaces root yet, so the mount guard is off.
|
||||||
|
# When utilidor is mounted, switch both lines together — never set the
|
||||||
|
# root onto a mount without also setting the guard, or a play that runs
|
||||||
|
# while the mount is down fills the root filesystem instead of failing.
|
||||||
|
# multica_workspaces_root: "/mnt/utilidor/multica/workspaces"
|
||||||
|
# multica_workspaces_root_mount: "/mnt/utilidor"
|
||||||
|
multica_agent_clis:
|
||||||
|
- claude
|
||||||
|
|
||||||
|
# --- Secret source ----------------------------------------------------
|
||||||
|
# This homelab keeps Ansible secrets in ansible-vault encrypted files, so
|
||||||
|
# that is the live form. One PAT per host (named daemon-<host>), held in
|
||||||
|
# the global vault (group_vars/all/vault) as a dictionary keyed by short
|
||||||
|
# hostname:
|
||||||
|
# vault_multica_pats: { haunted-mansion: mul_…, spaceship-earth: mul_… }
|
||||||
|
# A host with no entry fails the pre_task below, by name, before anything
|
||||||
|
# runs. The indirection keeps the name greppable and the file swappable.
|
||||||
|
multica_pat: "{{ vault_multica_pats[inventory_hostname_short] }}"
|
||||||
|
#
|
||||||
|
# Alternatives, if the backend ever consolidates. Each is a one-line
|
||||||
|
# change here; the role is untouched by any of them.
|
||||||
|
#
|
||||||
|
# HashiCorp Vault (community.hashi_vault):
|
||||||
|
# multica_pat: "{{ lookup('community.hashi_vault.vault_kv2_get',
|
||||||
|
# 'multica/agent-host').secret.pat }}"
|
||||||
|
#
|
||||||
|
# 1Password (community.general):
|
||||||
|
# multica_pat: "{{ lookup('community.general.onepassword',
|
||||||
|
# 'Multica Agent Host PAT', field='credential') }}"
|
||||||
|
#
|
||||||
|
# Environment variable on the control node:
|
||||||
|
# multica_pat: "{{ lookup('env', 'MULTICA_PAT') }}"
|
||||||
|
|
||||||
|
# The role's own PAT assert is no_log, so a missing dictionary entry would
|
||||||
|
# surface there only as "censored". This checks key presence, never the
|
||||||
|
# value, so its failure can name the host.
|
||||||
|
pre_tasks:
|
||||||
|
- name: Require a per-host Multica PAT in the vault
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- vault_multica_pats is defined
|
||||||
|
- vault_multica_pats is mapping
|
||||||
|
- inventory_hostname_short in vault_multica_pats
|
||||||
|
fail_msg: >-
|
||||||
|
No Multica PAT for {{ inventory_hostname_short }}: add
|
||||||
|
vault_multica_pats['{{ inventory_hostname_short }}'] to
|
||||||
|
group_vars/all/vault.
|
||||||
|
quiet: true
|
||||||
|
tags: [always, multica_pat_check]
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: multica_agent_host
|
||||||
@@ -0,0 +1,84 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# provision-wong-host.yml — spaceship-earth (WDWL-22)
|
||||||
|
#
|
||||||
|
# spaceship-earth runs exactly ONE agent: wong, the personal vault's librarian
|
||||||
|
# and its only writer. No other agent may be pinned to its runtime. The
|
||||||
|
# isolation is enforced by the OS, not by agent instructions: Obsidian Sync
|
||||||
|
# runs as `obsync`, and Wong's daemon user (multica) can reach inbox/ only.
|
||||||
|
#
|
||||||
|
# Run order on a fresh host:
|
||||||
|
# 1. ansible-playbook playbooks/provision-agent-host.yml --limit spaceship-earth
|
||||||
|
# (multica daemon user, Node.js, multica CLI, Claude Code)
|
||||||
|
# 2. ansible-playbook playbooks/provision-wong-host.yml
|
||||||
|
# (root LV growth, headless Obsidian, vault folder isolation)
|
||||||
|
#
|
||||||
|
# Step 2 needs Node.js and the multica user from step 1, and asserts both.
|
||||||
|
# The Obsidian account sign-in is manual; see roles/obsidian_headless/README.md.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: Grow the root filesystem to fill the disk
|
||||||
|
hosts: spaceship-earth
|
||||||
|
become: true
|
||||||
|
tags: [wong_disk]
|
||||||
|
|
||||||
|
vars:
|
||||||
|
root_vg: ubuntu-vg
|
||||||
|
root_lv: ubuntu-lv
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
- name: Disk | Find the PV backing the root VG
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
_root_pv: >-
|
||||||
|
{{ ansible_facts['lvm']['pvs'] | dict2items
|
||||||
|
| selectattr('value.vg', 'equalto', root_vg)
|
||||||
|
| map(attribute='key') | first }}
|
||||||
|
|
||||||
|
- name: Disk | Split the PV into disk and partition number
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
_root_disk: "{{ _root_pv | regex_replace('p?[0-9]+$', '') }}"
|
||||||
|
_root_partno: "{{ _root_pv | regex_search('[0-9]+$') }}"
|
||||||
|
|
||||||
|
- name: Disk | Install growpart
|
||||||
|
ansible.builtin.package:
|
||||||
|
name: cloud-guest-utils
|
||||||
|
state: present
|
||||||
|
|
||||||
|
# growpart exits 1 with "NOCHANGE" when the partition already fills the disk.
|
||||||
|
- name: Disk | Grow the partition
|
||||||
|
ansible.builtin.command:
|
||||||
|
argv: [growpart, "{{ _root_disk }}", "{{ _root_partno }}"]
|
||||||
|
register: _growpart
|
||||||
|
changed_when: _growpart.rc == 0 and 'CHANGED' in _growpart.stdout
|
||||||
|
failed_when: _growpart.rc != 0 and 'NOCHANGE' not in _growpart.stdout
|
||||||
|
|
||||||
|
- name: Disk | Grow the PV and VG
|
||||||
|
community.general.lvg:
|
||||||
|
vg: "{{ root_vg }}"
|
||||||
|
pvs: "{{ _root_pv }}"
|
||||||
|
pvresize: true
|
||||||
|
|
||||||
|
- name: Disk | Extend the root LV and its filesystem into the free space
|
||||||
|
community.general.lvol:
|
||||||
|
vg: "{{ root_vg }}"
|
||||||
|
lv: "{{ root_lv }}"
|
||||||
|
size: +100%FREE
|
||||||
|
resizefs: true
|
||||||
|
|
||||||
|
- name: Headless Obsidian Sync with vault folder isolation
|
||||||
|
hosts: spaceship-earth
|
||||||
|
become: true
|
||||||
|
tags: [obsidian]
|
||||||
|
|
||||||
|
vars:
|
||||||
|
obsidian_headless_vault_path: /srv/obsidian/vault
|
||||||
|
obsidian_headless_device_name: spaceship-earth
|
||||||
|
obsidian_headless_private_folders:
|
||||||
|
- everpure
|
||||||
|
- wip
|
||||||
|
obsidian_headless_shared_folders:
|
||||||
|
- path: inbox
|
||||||
|
user: multica
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: obsidian_headless
|
||||||
@@ -1,77 +0,0 @@
|
|||||||
---
|
|
||||||
# ------------------------------------------------------------------------------
|
|
||||||
# FILE: roles/common/tasks/main.yml
|
|
||||||
# DESCRIPTION: Baseline configuration applied to all managed Ubuntu hosts.
|
|
||||||
# Handles hostname, timezone, core packages, NTP, ansible user,
|
|
||||||
# and optional LVM root volume expansion.
|
|
||||||
# ------------------------------------------------------------------------------
|
|
||||||
|
|
||||||
- name: Set hostname
|
|
||||||
hostname:
|
|
||||||
name: "{{ inventory_hostname | replace('_', '-') }}"
|
|
||||||
|
|
||||||
- name: Set timezone
|
|
||||||
timezone:
|
|
||||||
name: "{{ common_timezone }}"
|
|
||||||
|
|
||||||
- name: Update apt cache
|
|
||||||
apt:
|
|
||||||
update_cache: yes
|
|
||||||
cache_valid_time: 3600
|
|
||||||
|
|
||||||
- name: Install base utility packages
|
|
||||||
apt:
|
|
||||||
name: "{{ common_packages }}"
|
|
||||||
state: present
|
|
||||||
|
|
||||||
- name: Install chrony
|
|
||||||
apt:
|
|
||||||
name: chrony
|
|
||||||
state: present
|
|
||||||
|
|
||||||
- name: Configure chrony to use sundial
|
|
||||||
template:
|
|
||||||
src: chrony.conf.j2
|
|
||||||
dest: /etc/chrony/chrony.conf
|
|
||||||
mode: '0644'
|
|
||||||
notify: restart chrony
|
|
||||||
|
|
||||||
- name: Ensure chrony is enabled and running
|
|
||||||
systemd:
|
|
||||||
name: chrony
|
|
||||||
state: started
|
|
||||||
enabled: yes
|
|
||||||
|
|
||||||
- name: Ensure ansible user has passwordless sudo
|
|
||||||
lineinfile:
|
|
||||||
path: /etc/sudoers.d/{{ ansible_user }}
|
|
||||||
line: "{{ ansible_user }} ALL=(ALL) NOPASSWD:ALL"
|
|
||||||
create: yes
|
|
||||||
mode: '0440'
|
|
||||||
validate: 'visudo -cf %s'
|
|
||||||
|
|
||||||
# ------------------------------------------------------------------------------
|
|
||||||
# LVM root volume expansion
|
|
||||||
# Extends the root PV to the full disk size and grows the LV + filesystem.
|
|
||||||
# This codifies what was previously done manually after provisioning.
|
|
||||||
# Runs only when common_expand_root_lvm is true (default: true).
|
|
||||||
# Safe to re-run — pvresize and lvextend are idempotent when already at max.
|
|
||||||
# ------------------------------------------------------------------------------
|
|
||||||
|
|
||||||
- name: Expand root PV to full disk size
|
|
||||||
command: pvresize {{ common_root_pv }}
|
|
||||||
register: pvresize_result
|
|
||||||
changed_when: "'changed' in pvresize_result.stdout or pvresize_result.rc == 0"
|
|
||||||
when: common_expand_root_lvm | bool
|
|
||||||
|
|
||||||
- name: Extend root LV to 100% of free VG space
|
|
||||||
lvol:
|
|
||||||
vg: "{{ common_root_vg }}"
|
|
||||||
lv: "{{ common_root_lv }}"
|
|
||||||
size: +100%FREE
|
|
||||||
resizefs: yes
|
|
||||||
when:
|
|
||||||
- common_expand_root_lvm | bool
|
|
||||||
ignore_errors: yes
|
|
||||||
# ignore_errors because lvextend returns non-zero when already at max size.
|
|
||||||
# resizefs: yes handles the resize2fs call inline — no separate task needed.
|
|
||||||
@@ -1,5 +0,0 @@
|
|||||||
---
|
|
||||||
# file: roles/semaphore/defaults/main.yml
|
|
||||||
|
|
||||||
semaphore_compose_dir: /opt/docker/semaphore
|
|
||||||
semaphore_ssh_key_file: "~/.ssh/ansible"
|
|
||||||
@@ -1,7 +0,0 @@
|
|||||||
---
|
|
||||||
# file: roles/semaphore/handlers/main.yml
|
|
||||||
|
|
||||||
- name: Restart Semaphore
|
|
||||||
community.docker.docker_compose_v2:
|
|
||||||
project_src: "{{ semaphore_compose_dir }}"
|
|
||||||
state: restarted
|
|
||||||
@@ -1,50 +0,0 @@
|
|||||||
---
|
|
||||||
# file: roles/semaphore/tasks/main.yml
|
|
||||||
|
|
||||||
- name: Create Semaphore directory
|
|
||||||
ansible.builtin.file:
|
|
||||||
path: "{{ semaphore_compose_dir }}"
|
|
||||||
state: directory
|
|
||||||
owner: wed
|
|
||||||
group: docker
|
|
||||||
mode: '0755'
|
|
||||||
|
|
||||||
- name: Copy Compose file from boilerplate
|
|
||||||
ansible.builtin.copy:
|
|
||||||
src: "{{ playbook_dir }}/../../boilerplates/semaphore/compose.yaml"
|
|
||||||
dest: "{{ semaphore_compose_dir }}/compose.yaml"
|
|
||||||
owner: wed
|
|
||||||
group: docker
|
|
||||||
mode: '0644'
|
|
||||||
|
|
||||||
- name: Deploy Semaphore .env file
|
|
||||||
ansible.builtin.template:
|
|
||||||
src: env.j2
|
|
||||||
dest: "{{ semaphore_compose_dir }}/.env"
|
|
||||||
owner: wed
|
|
||||||
group: docker
|
|
||||||
mode: '0600'
|
|
||||||
|
|
||||||
- name: Copy SSH key for Ansible authentication
|
|
||||||
ansible.builtin.copy:
|
|
||||||
src: "{{ semaphore_ssh_key_file }}"
|
|
||||||
dest: "{{ semaphore_compose_dir }}/ansible_key"
|
|
||||||
owner: "1001"
|
|
||||||
group: "1001"
|
|
||||||
mode: '0600'
|
|
||||||
|
|
||||||
- name: Start Semaphore containers
|
|
||||||
community.docker.docker_compose_v2:
|
|
||||||
project_src: "{{ semaphore_compose_dir }}"
|
|
||||||
state: present
|
|
||||||
register: semaphore_compose
|
|
||||||
|
|
||||||
- name: Wait for Semaphore to be ready
|
|
||||||
ansible.builtin.uri:
|
|
||||||
url: "http://localhost:3000/api/ping"
|
|
||||||
method: GET
|
|
||||||
status_code: 200
|
|
||||||
register: semaphore_health
|
|
||||||
retries: 48
|
|
||||||
delay: 5
|
|
||||||
until: semaphore_health.status == 200
|
|
||||||
@@ -1,3 +0,0 @@
|
|||||||
DATABASE_PASSWORD={{ vault_semaphore_database_password }}
|
|
||||||
SEMAPHORE_ADMIN_PASSWORD={{ vault_semaphore_admin_password }}
|
|
||||||
SEMAPHORE_ACCESS_KEY_ENCRYPTION={{ vault_semaphore_access_key_encryption }}
|
|
||||||
@@ -1,21 +1,6 @@
|
|||||||
# requirements.yml
|
|
||||||
---
|
---
|
||||||
collections:
|
collections:
|
||||||
- name: community.general
|
- name: containers.podman
|
||||||
version: 11.4.1
|
version: ">=1.10.0"
|
||||||
|
- name: effectivelywild.technitium_dns
|
||||||
# - name: nccurry.openshift
|
version: ">=1.1.0"
|
||||||
# version: 1.4.0
|
|
||||||
|
|
||||||
- name: somaz94.ansible_k8s_iac_tool
|
|
||||||
version: 1.1.6
|
|
||||||
|
|
||||||
# - name: prometheus.prometheus
|
|
||||||
# version: 0.27.0
|
|
||||||
|
|
||||||
- name: kubernetes.core
|
|
||||||
|
|
||||||
- name: community.proxmox
|
|
||||||
version: 1.4.0
|
|
||||||
|
|
||||||
- name: effectivelywild.technitium_dns
|
|
||||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
@@ -0,0 +1,35 @@
|
|||||||
|
# claude_code role
|
||||||
|
|
||||||
|
Installs [Claude Code](https://code.claude.com/docs/en/setup) on Ubuntu 20.04+ / Debian 10+ (x64 or ARM64, 4 GB+ RAM).
|
||||||
|
|
||||||
|
## Methods
|
||||||
|
|
||||||
|
| `claude_code_install_method` | What it does | Updates |
|
||||||
|
|---|---|---|
|
||||||
|
| `apt` (default) | Adds Anthropic's signed apt repo (stable or latest channel) and installs the `claude-code` package system-wide. Verifies the signing-key fingerprint before trusting it. | `apt upgrade` / set `claude_code_package_state: latest` |
|
||||||
|
| `native` | Runs Anthropic's installer as `claude_code_user`; binary lands in `~/.local/bin/claude`. | Self-updates in the background |
|
||||||
|
|
||||||
|
## Key variables (see `defaults/main.yml`)
|
||||||
|
|
||||||
|
- `claude_code_apt_channel`: `stable` (about a week behind, skips bad releases) or `latest`
|
||||||
|
- `claude_code_package_state`: `present` or `latest`
|
||||||
|
- `claude_code_native_version`: `latest`, `stable`, or a pinned version like `2.1.89`
|
||||||
|
- `claude_code_settings`: optional dict written to `~/.claude/settings.json` (overwrites the file)
|
||||||
|
|
||||||
|
## Use
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cp inventory.ini.example inventory.ini # edit hosts
|
||||||
|
ansible-playbook -i inventory.ini install-claude.yml --check # dry run
|
||||||
|
ansible-playbook -i inventory.ini install-claude.yml
|
||||||
|
```
|
||||||
|
|
||||||
|
The remote user needs sudo for the `apt` method.
|
||||||
|
|
||||||
|
## After install: authenticate (not automated)
|
||||||
|
|
||||||
|
Run `claude` once on the server and follow the login prompt, or export `ANTHROPIC_API_KEY`
|
||||||
|
for the user (store it in Ansible Vault, not in the repo). A Pro, Max, Team, Enterprise or
|
||||||
|
Console account is required; the free claude.ai plan does not include Claude Code.
|
||||||
|
|
||||||
|
Verify with `claude --version` and `claude doctor`.
|
||||||
@@ -0,0 +1,39 @@
|
|||||||
|
# roles/claude_code/defaults/main.yml
|
||||||
|
---
|
||||||
|
# How to install Claude Code:
|
||||||
|
# apt - signed Anthropic apt repo, system-wide, upgraded via apt (recommended for servers)
|
||||||
|
# native - Anthropic's installer script, per-user in ~/.local/bin, self-updating
|
||||||
|
claude_code_install_method: apt
|
||||||
|
|
||||||
|
# ---- apt method -------------------------------------------------------------
|
||||||
|
# Release channel: "stable" (~1 week behind, skips bad releases) or "latest"
|
||||||
|
claude_code_apt_channel: stable
|
||||||
|
# "present" installs once; "latest" upgrades on every run
|
||||||
|
claude_code_package_state: present
|
||||||
|
|
||||||
|
claude_code_apt_key_url: https://downloads.claude.ai/keys/claude-code.asc
|
||||||
|
claude_code_apt_key_path: /etc/apt/keyrings/claude-code.asc
|
||||||
|
# Fingerprint published in Anthropic's docs; the role refuses to continue if it differs
|
||||||
|
claude_code_apt_key_fingerprint: "31DDDE24DDFAB679F42D7BD2BAA929FF1A7ECACE"
|
||||||
|
claude_code_apt_repo_base: https://downloads.claude.ai/claude-code/apt
|
||||||
|
|
||||||
|
# ---- native method ----------------------------------------------------------
|
||||||
|
# User the native installer runs as
|
||||||
|
claude_code_user: "{{ ansible_user_id }}"
|
||||||
|
# "latest", "stable", or a specific version such as "2.1.89"
|
||||||
|
claude_code_native_version: latest
|
||||||
|
|
||||||
|
# ---- common -----------------------------------------------------------------
|
||||||
|
claude_code_prereq_packages:
|
||||||
|
- curl
|
||||||
|
- ca-certificates
|
||||||
|
- gnupg
|
||||||
|
|
||||||
|
# Optional: content for ~/.claude/settings.json of claude_code_settings_user.
|
||||||
|
# Empty dict = don't touch the file. NOTE: when set, the file is overwritten.
|
||||||
|
# Example: { "autoUpdatesChannel": "stable", "env": { "DISABLE_AUTOUPDATER": "1" } }
|
||||||
|
claude_code_settings: {}
|
||||||
|
claude_code_settings_user: "{{ claude_code_user }}"
|
||||||
|
|
||||||
|
# Run `claude --version` at the end and fail if it doesn't work
|
||||||
|
claude_code_verify: true
|
||||||
@@ -0,0 +1,15 @@
|
|||||||
|
# roles/claude_code/meta/main.yml
|
||||||
|
---
|
||||||
|
galaxy_info:
|
||||||
|
role_name: claude_code
|
||||||
|
author: ryan
|
||||||
|
description: Install Claude Code on Ubuntu/Debian servers (signed apt repo or native installer)
|
||||||
|
license: MIT
|
||||||
|
min_ansible_version: "2.14"
|
||||||
|
platforms:
|
||||||
|
- name: Ubuntu
|
||||||
|
versions: [focal, jammy, noble]
|
||||||
|
- name: Debian
|
||||||
|
versions: [buster, bullseye, bookworm]
|
||||||
|
galaxy_tags: [claude, ai, cli]
|
||||||
|
dependencies: []
|
||||||
@@ -0,0 +1,70 @@
|
|||||||
|
# roles/claude_code/tasks/apt.yml
|
||||||
|
---
|
||||||
|
- name: Create apt keyrings directory
|
||||||
|
ansible.builtin.file:
|
||||||
|
path: /etc/apt/keyrings
|
||||||
|
state: directory
|
||||||
|
mode: "0755"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Download Anthropic release signing key
|
||||||
|
ansible.builtin.get_url:
|
||||||
|
url: "{{ claude_code_apt_key_url }}"
|
||||||
|
dest: "{{ claude_code_apt_key_path }}"
|
||||||
|
mode: "0644"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Read key fingerprint
|
||||||
|
ansible.builtin.shell:
|
||||||
|
cmd: |
|
||||||
|
set -o pipefail
|
||||||
|
gpg --show-keys --with-colons {{ claude_code_apt_key_path | quote }} | awk -F':' '/^fpr/ {print $10; exit}'
|
||||||
|
executable: /bin/bash
|
||||||
|
register: claude_code_key_fpr
|
||||||
|
changed_when: false
|
||||||
|
check_mode: false
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Refuse to continue if the key fingerprint does not match
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- claude_code_key_fpr.stdout | trim | upper == claude_code_apt_key_fingerprint | upper
|
||||||
|
fail_msg: >-
|
||||||
|
Signing key fingerprint mismatch: got '{{ claude_code_key_fpr.stdout | trim }}',
|
||||||
|
expected '{{ claude_code_apt_key_fingerprint }}'. Removing the key file.
|
||||||
|
quiet: true
|
||||||
|
register: claude_code_key_check
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: Remove untrusted key file
|
||||||
|
ansible.builtin.file:
|
||||||
|
path: "{{ claude_code_apt_key_path }}"
|
||||||
|
state: absent
|
||||||
|
become: true
|
||||||
|
when: claude_code_key_check is failed
|
||||||
|
|
||||||
|
- name: Stop if key check failed
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "{{ claude_code_key_check.msg }}"
|
||||||
|
when: claude_code_key_check is failed
|
||||||
|
|
||||||
|
- name: Configure Claude Code apt repository
|
||||||
|
ansible.builtin.apt_repository:
|
||||||
|
repo: >-
|
||||||
|
deb [signed-by={{ claude_code_apt_key_path }}]
|
||||||
|
{{ claude_code_apt_repo_base }}/{{ claude_code_apt_channel }}
|
||||||
|
{{ claude_code_apt_channel }} main
|
||||||
|
filename: claude-code
|
||||||
|
state: present
|
||||||
|
update_cache: true
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Install claude-code package
|
||||||
|
ansible.builtin.apt:
|
||||||
|
name: claude-code
|
||||||
|
state: "{{ claude_code_package_state }}"
|
||||||
|
become: true
|
||||||
@@ -0,0 +1,44 @@
|
|||||||
|
# roles/claude_code/tasks/main.yml
|
||||||
|
---
|
||||||
|
- name: Assert a supported install method
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- claude_code_install_method in ['apt', 'native']
|
||||||
|
- claude_code_apt_channel in ['stable', 'latest']
|
||||||
|
fail_msg: "claude_code_install_method must be apt|native and claude_code_apt_channel stable|latest"
|
||||||
|
quiet: true
|
||||||
|
|
||||||
|
- name: Assert a supported OS (Ubuntu 20.04+ / Debian 10+)
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- ansible_facts['os_family'] == 'Debian'
|
||||||
|
- >-
|
||||||
|
(ansible_facts['distribution'] == 'Ubuntu' and ansible_facts['distribution_version'] is version('20.04', '>='))
|
||||||
|
or (ansible_facts['distribution'] == 'Debian' and ansible_facts['distribution_version'] is version('10', '>='))
|
||||||
|
- ansible_facts['architecture'] in ['x86_64', 'aarch64']
|
||||||
|
fail_msg: "Claude Code needs Ubuntu 20.04+/Debian 10+ on x64 or ARM64"
|
||||||
|
quiet: true
|
||||||
|
|
||||||
|
- name: Install prerequisite packages
|
||||||
|
ansible.builtin.apt:
|
||||||
|
name: "{{ claude_code_prereq_packages }}"
|
||||||
|
state: present
|
||||||
|
update_cache: true
|
||||||
|
cache_valid_time: 3600
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Install via apt repository
|
||||||
|
ansible.builtin.include_tasks: apt.yml
|
||||||
|
when: claude_code_install_method == 'apt'
|
||||||
|
|
||||||
|
- name: Install via native installer
|
||||||
|
ansible.builtin.include_tasks: native.yml
|
||||||
|
when: claude_code_install_method == 'native'
|
||||||
|
|
||||||
|
- name: Write Claude Code settings
|
||||||
|
ansible.builtin.include_tasks: settings.yml
|
||||||
|
when: claude_code_settings | length > 0
|
||||||
|
|
||||||
|
- name: Verify installation
|
||||||
|
ansible.builtin.include_tasks: verify.yml
|
||||||
|
when: claude_code_verify | bool
|
||||||
@@ -0,0 +1,20 @@
|
|||||||
|
# roles/claude_code/tasks/native.yml
|
||||||
|
---
|
||||||
|
- name: Install Claude Code with the native installer
|
||||||
|
ansible.builtin.shell:
|
||||||
|
cmd: set -o pipefail; curl -fsSL https://claude.ai/install.sh | bash -s {{ claude_code_native_version | quote }}
|
||||||
|
executable: /bin/bash
|
||||||
|
creates: "~{{ claude_code_user }}/.local/bin/claude"
|
||||||
|
become: true
|
||||||
|
become_user: "{{ claude_code_user }}"
|
||||||
|
|
||||||
|
- name: Put ~/.local/bin on PATH for login shells
|
||||||
|
ansible.builtin.copy:
|
||||||
|
dest: /etc/profile.d/claude-code.sh
|
||||||
|
content: |
|
||||||
|
# Managed by Ansible (claude_code role)
|
||||||
|
case ":$PATH:" in *":$HOME/.local/bin:"*) ;; *) export PATH="$HOME/.local/bin:$PATH" ;; esac
|
||||||
|
mode: "0644"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
become: true
|
||||||
@@ -0,0 +1,22 @@
|
|||||||
|
# roles/claude_code/tasks/settings.yml
|
||||||
|
---
|
||||||
|
- name: Look up settings user
|
||||||
|
ansible.builtin.getent:
|
||||||
|
database: passwd
|
||||||
|
key: "{{ claude_code_settings_user }}"
|
||||||
|
|
||||||
|
- name: Create ~/.claude directory
|
||||||
|
ansible.builtin.file:
|
||||||
|
path: "{{ ansible_facts['getent_passwd'][claude_code_settings_user][4] }}/.claude"
|
||||||
|
state: directory
|
||||||
|
mode: "0700"
|
||||||
|
owner: "{{ claude_code_settings_user }}"
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Write ~/.claude/settings.json
|
||||||
|
ansible.builtin.copy:
|
||||||
|
dest: "{{ ansible_facts['getent_passwd'][claude_code_settings_user][4] }}/.claude/settings.json"
|
||||||
|
content: "{{ claude_code_settings | to_nice_json }}\n"
|
||||||
|
mode: "0600"
|
||||||
|
owner: "{{ claude_code_settings_user }}"
|
||||||
|
become: true
|
||||||
@@ -0,0 +1,17 @@
|
|||||||
|
# roles/claude_code/tasks/verify.yml
|
||||||
|
---
|
||||||
|
- name: Check claude --version
|
||||||
|
ansible.builtin.shell:
|
||||||
|
cmd: |
|
||||||
|
if command -v claude >/dev/null 2>&1; then claude --version
|
||||||
|
else "$HOME/.local/bin/claude" --version; fi
|
||||||
|
executable: /bin/bash
|
||||||
|
become: "{{ claude_code_install_method == 'native' }}"
|
||||||
|
become_user: "{{ claude_code_user if claude_code_install_method == 'native' else omit }}"
|
||||||
|
register: claude_code_version_out
|
||||||
|
changed_when: false
|
||||||
|
check_mode: false
|
||||||
|
|
||||||
|
- name: Show installed version
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "{{ claude_code_version_out.stdout }}"
|
||||||
+2
@@ -8,6 +8,7 @@ common_timezone: America/Chicago
|
|||||||
common_ntp_server: "sundial.local.mk-labs.cloud"
|
common_ntp_server: "sundial.local.mk-labs.cloud"
|
||||||
|
|
||||||
common_packages:
|
common_packages:
|
||||||
|
- acl
|
||||||
- curl
|
- curl
|
||||||
- wget
|
- wget
|
||||||
- vim
|
- vim
|
||||||
@@ -21,6 +22,7 @@ common_packages:
|
|||||||
- net-tools
|
- net-tools
|
||||||
- dnsutils
|
- dnsutils
|
||||||
- lvm2
|
- lvm2
|
||||||
|
- cloud-guest-utils
|
||||||
|
|
||||||
# ------------------------------------------------------------------------------
|
# ------------------------------------------------------------------------------
|
||||||
# LVM root volume expansion
|
# LVM root volume expansion
|
||||||
File renamed without changes.
File renamed without changes.
@@ -0,0 +1,21 @@
|
|||||||
|
- name: Create cast group
|
||||||
|
ansible.builtin.group:
|
||||||
|
name: cast
|
||||||
|
state: present
|
||||||
|
system: true
|
||||||
|
|
||||||
|
- name: Create cast user
|
||||||
|
ansible.builtin.user:
|
||||||
|
name: cast
|
||||||
|
group: cast
|
||||||
|
shell: /bin/bash
|
||||||
|
create_home: true
|
||||||
|
state: present
|
||||||
|
|
||||||
|
- name: Ensure cast user has passwordless sudo
|
||||||
|
ansible.builtin.lineinfile:
|
||||||
|
path: /etc/sudoers.d/cast
|
||||||
|
line: "cast ALL=(ALL) NOPASSWD:ALL"
|
||||||
|
create: yes
|
||||||
|
mode: '0440'
|
||||||
|
validate: 'visudo -cf %s'
|
||||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
@@ -0,0 +1,12 @@
|
|||||||
|
---
|
||||||
|
# Timezone
|
||||||
|
timezone: "UTC"
|
||||||
|
|
||||||
|
# Packages to ensure are present
|
||||||
|
baseline_packages:
|
||||||
|
- chrony
|
||||||
|
- vim
|
||||||
|
- htop
|
||||||
|
- curl
|
||||||
|
- wget
|
||||||
|
- rsync
|
||||||
@@ -0,0 +1,6 @@
|
|||||||
|
---
|
||||||
|
- name: Restart sshd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: sshd
|
||||||
|
state: restarted
|
||||||
|
become: true
|
||||||
@@ -0,0 +1,32 @@
|
|||||||
|
---
|
||||||
|
- name: Set timezone
|
||||||
|
community.general.timezone:
|
||||||
|
name: "{{ timezone }}"
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Enable and start chronyd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: chronyd
|
||||||
|
state: started
|
||||||
|
enabled: true
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Update all packages
|
||||||
|
ansible.builtin.package:
|
||||||
|
name: "*"
|
||||||
|
state: latest
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Install baseline packages
|
||||||
|
ansible.builtin.package:
|
||||||
|
name: "{{ baseline_packages }}"
|
||||||
|
state: present
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Disable root SSH login
|
||||||
|
ansible.builtin.lineinfile:
|
||||||
|
path: /etc/ssh/sshd_config
|
||||||
|
regexp: '^PermitRootLogin'
|
||||||
|
line: "PermitRootLogin no"
|
||||||
|
become: true
|
||||||
|
notify: Restart sshd
|
||||||
@@ -0,0 +1,515 @@
|
|||||||
|
# deploy-vllm
|
||||||
|
|
||||||
|
Idempotent Ansible role that deploys a vLLM OpenAI-compatible inference
|
||||||
|
server. Written for astro-orbiter (RTX 3090, 24GB VRAM, 64GB RAM, Ubuntu
|
||||||
|
24.04) and designed for reuse on the planned Mac Mini M4 host later this
|
||||||
|
week (see "Portability" below).
|
||||||
|
|
||||||
|
Supersedes the manual, pre-role state left behind by earlier vLLM
|
||||||
|
experiments (`/home/jarvis/vllm-env`, bitsandbytes, gemma-2-27b — see
|
||||||
|
`homelab-llm-inference`/`homelab-llm-serving` skills for that history). This
|
||||||
|
role uses a **fresh venv** (`vllm_venv_path`, default `~/vllm-serve-env`) and
|
||||||
|
**AWQ pre-quantized models** — no bitsandbytes, no on-the-fly quantization,
|
||||||
|
no repeat of the OOM incident from the earlier Gemma-2-27B attempt.
|
||||||
|
|
||||||
|
## Phases
|
||||||
|
|
||||||
|
| Phase | File | What it does |
|
||||||
|
|---|---|---|
|
||||||
|
| 1 | `tasks/dependencies.yml` | System Python 3.10+, dedicated venv, `pip install vllm>=0.5.0`, verifies `nvidia-smi` and `torch.cuda.is_available()` |
|
||||||
|
| 2 | `tasks/models.yml` | Downloads each `enabled: true` model in `vllm_models` via `hf download` (huggingface_hub CLI) into `~/.vllm-cache`, verifies the snapshot landed and reports on-disk size |
|
||||||
|
| 3 | `tasks/api-key.yml` | Reads the API key from 1Password (`op://mk-labs/vllm/api-key`) on the **controller**, writes it to `/etc/vllm/api-key.env` (root:root, 0600) on the target |
|
||||||
|
| 4 | `tasks/systemd.yml` | Renders and installs one systemd unit per enabled model (`vllm.service` for the `role: primary` model, `vllm-<id>.service` for others) |
|
||||||
|
| 5 | `tasks/verify.yml` | Only runs when `vllm_service_state=started`. Waits for `/health` (up to 5 min — torch.compile warmup), checks `/v1/models`, runs a live completion, scans `journalctl` for errors |
|
||||||
|
|
||||||
|
Run all phases: `ansible-playbook -i inventory.yml playbooks/day1_deploy_vllm.yml --limit astro-orbiter`
|
||||||
|
Run one phase: `--tags vllm-dependencies` / `vllm-models` / `vllm-api-key` / `vllm-systemd` / `vllm-verify`
|
||||||
|
|
||||||
|
## Deliberate staging-first default
|
||||||
|
|
||||||
|
`vllm_service_state` defaults to `stopped`. A default run **stages
|
||||||
|
everything** (venv, model weights, API key file, systemd unit) but does
|
||||||
|
**not** start the service or touch production traffic. This matches the
|
||||||
|
astro-orbiter cutover plan: llama-swap is live production serving (Qwen3.8-27B
|
||||||
|
+ nomic-embed for Hindsight) — vLLM must be deployed and validated on a
|
||||||
|
side port/inactive unit before anything is cut over.
|
||||||
|
|
||||||
|
To start and validate:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
ansible-playbook -i inventory.yml playbooks/day1_deploy_vllm.yml \
|
||||||
|
--limit astro-orbiter --extra-vars "vllm_service_state=started"
|
||||||
|
```
|
||||||
|
|
||||||
|
This starts the systemd unit(s), enables them, and runs Phase 5 verification
|
||||||
|
(health, `/v1/models`, live completion, clean journalctl).
|
||||||
|
|
||||||
|
**Cutover of consumers (Hermes profiles, Hindsight embedding config, any
|
||||||
|
hardcoded `:8001`/`:5805` references) to the new `:8000` vLLM endpoint is a
|
||||||
|
separate, explicit step outside this role** — do this only after Phase 5
|
||||||
|
passes cleanly. Do not tear down llama-swap until consumers are confirmed
|
||||||
|
working end-to-end against vLLM.
|
||||||
|
|
||||||
|
## Model roster (`vllm_models` in defaults/main.yml)
|
||||||
|
|
||||||
|
vLLM 0.5.x-0.28.x serves **one model per process** — multi-model = multiple
|
||||||
|
systemd units on distinct ports, not a single multiplexed server (unlike
|
||||||
|
llama-swap's matrix DSL). Today's phase enables only the primary model;
|
||||||
|
flip `enabled: true` on the others as VRAM allows (see "Phased Strategy"):
|
||||||
|
|
||||||
|
**⚠️ Table below reflects the ORIGINAL Qwen2.5-32B deployment. As of
|
||||||
|
2026-09-01 (t_r1d32b_swap) the primary model is
|
||||||
|
`DeepSeek-R1-Distill-Qwen-32B-AWQ`, single-model only (nomic-embed also
|
||||||
|
disabled) — see the "SUPERSEDED" section further down for current state.**
|
||||||
|
|
||||||
|
| id | hf_repo | role | port | quant | enabled |
|
||||||
|
|---|---|---|---|---|---|
|
||||||
|
| Qwen2.5-32B-Instruct-AWQ | Qwen/Qwen2.5-32B-Instruct-AWQ | primary | 8000 | awq | **true** |
|
||||||
|
| Qwen3-8B-AWQ | Qwen/Qwen3-8B-AWQ | aux | 8010 | awq | false |
|
||||||
|
| nomic-embed-text-v1.5 | nomic-ai/nomic-embed-text-v1.5 | embedding | 8020 | none | false |
|
||||||
|
|
||||||
|
**Note on the original spec's model choices:** the task body named
|
||||||
|
`Qwen/Qwen2.5-32B-Instruct` and `Qwen/Qwen3-8B-Instruct` (bf16, unquantized).
|
||||||
|
vLLM does not do on-the-fly quantization safely on this host (bitsandbytes
|
||||||
|
OOM history — see `homelab-llm-inference` skill Pitfalls) and unquantized
|
||||||
|
bf16 32B does not fit a 24GB card at all (~65GB). This role instead deploys
|
||||||
|
the **official Qwen AWQ pre-quantized variants**
|
||||||
|
(`Qwen/Qwen2.5-32B-Instruct-AWQ`, `Qwen/Qwen3-8B-AWQ`), which vLLM natively
|
||||||
|
supports (`--quantization awq`) and which fit the VRAM budget:
|
||||||
|
|
||||||
|
- Qwen2.5-32B-Instruct-AWQ: ~19.3GB on disk, fits with ~5GB headroom at 24GB
|
||||||
|
- Qwen3-8B-AWQ: ~6GB VRAM per llm-explorer
|
||||||
|
- nomic-embed-text-v1.5: ~300MB, vLLM serves it via `--convert embed` pooling
|
||||||
|
(see vLLM embedding docs) — **not yet wired into this role's systemd
|
||||||
|
template**; the embedding model needs `--task embed` / `--convert embed`
|
||||||
|
flags that differ from the completion-serving template. Flagged as a
|
||||||
|
follow-up before `enabled: true` is flipped on it (see Known Gaps below).
|
||||||
|
|
||||||
|
## Known Gaps / Follow-ups
|
||||||
|
|
||||||
|
- Quarterly API key rotation is documented (`/etc/vllm/API_KEY_ROTATION.md`
|
||||||
|
on the target, rendered by `tasks/api-key.yml`) but not automated — no cron
|
||||||
|
job exists to force rotation on a schedule. Consider a follow-up cron task
|
||||||
|
if Nick Fury wants this enforced rather than just documented.
|
||||||
|
- `vllm_service_enabled` defaults to `false` deliberately — see "Deliberate
|
||||||
|
staging-first default" above. Flip together with the cutover step, not
|
||||||
|
before.
|
||||||
|
- **vLLM cannot replace llama-swap's full model roster on this card — see
|
||||||
|
"Critical architectural finding" section below for the full incident.**
|
||||||
|
Short version: vLLM's one-model-per-process design plus llama-swap's own
|
||||||
|
VRAM needs exceed this 24GB card's capacity when both must serve real
|
||||||
|
models simultaneously. Full llama-swap teardown (t_6dff1ecc) cannot
|
||||||
|
proceed until a human decides the aux-model + VRAM strategy.
|
||||||
|
|
||||||
|
## Embedding-mode support (t_e6facb19, 2026-08-31)
|
||||||
|
|
||||||
|
`vllm.service.j2` now branches on `role: embedding` entries in `vllm_models`:
|
||||||
|
adds `--runner pooling --convert embed` (vLLM's embedding-serving flags —
|
||||||
|
see https://docs.vllm.ai/en/latest/models/pooling_models/embed/) and
|
||||||
|
`--no-enable-prefix-caching` (prefix caching is a completions-only
|
||||||
|
optimization; irrelevant and safely disabled for pooling). An additional
|
||||||
|
per-model `trust_remote_code: true` toggle renders `--trust-remote-code`
|
||||||
|
when set — required for `nomic-ai/nomic-embed-text-v1.5`, which ships
|
||||||
|
custom `NomicBertModel` modeling code on its HF repo.
|
||||||
|
|
||||||
|
**Verification does NOT run `/v1/completions` against embedding-mode
|
||||||
|
instances** (they don't serve that endpoint — a completions request 400s
|
||||||
|
immediately). `tasks/verify.yml` splits `vllm_enabled_models` by `role` and
|
||||||
|
runs the appropriate smoke test per group: completions models get the
|
||||||
|
`/v1/completions` "capital of France" test; embedding models get a real
|
||||||
|
`/v1/embeddings` POST with an `ansible.builtin.assert` on a non-empty
|
||||||
|
`data[0].embedding` array (not just HTTP 200 — an empty/malformed vector
|
||||||
|
would still 200).
|
||||||
|
|
||||||
|
**Critical VRAM finding: co-resident completions + embedding vLLM processes
|
||||||
|
need MORE headroom than either alone, and CUDA graph capture is the failure
|
||||||
|
mode, not KV cache sizing.** Enabling `nomic-embed-text-v1.5` alongside the
|
||||||
|
primary Qwen2.5-32B model at the role-default `gpu_memory_utilization: 0.95`
|
||||||
|
crash-looped repeatedly:
|
||||||
|
- First failure: `torch.OutOfMemoryError` during `capture_model()` (CUDA
|
||||||
|
graph capture) — KV cache sizing itself succeeded (14,720 tokens
|
||||||
|
allocated), but graph capture needed ~20MiB more than the 0.95 budget had
|
||||||
|
left once nomic's embedding process (814MiB actual, not the nominal
|
||||||
|
~300MB estimate in the model roster table) claimed its share.
|
||||||
|
- Fix attempt 1: added a per-model `enforce_eager: true` template branch
|
||||||
|
(`--enforce-eager` skips CUDA graph capture entirely) — this stopped the
|
||||||
|
graph-capture OOM but the combined processes still landed at only
|
||||||
|
~847MiB genuinely free out of 24,576MiB, and both services crash-looped
|
||||||
|
6-7 times during warmup before finally stabilizing (each attempt leaves
|
||||||
|
transient VRAM that the next attempt fights over, extending time-to-stable
|
||||||
|
well past a single health-check retry window).
|
||||||
|
- Fix attempt 2 (final, verified stable): lowered the primary model's
|
||||||
|
`gpu_memory_utilization` from 0.95 to **0.90** (host_vars override) in
|
||||||
|
addition to `enforce_eager: true`. Result: clean single-attempt start for
|
||||||
|
both services, `NRestarts=0`, ~2GB genuinely free (22,577MiB used /
|
||||||
|
24,576MiB total). Confirmed via `systemctl show <unit> -p NRestarts` after
|
||||||
|
a full stop/start cycle — 0.95 was NOT a fluke of Restart=always masking
|
||||||
|
the underlying fragility; 0.90 is a real, reproducible fix.
|
||||||
|
- **Takeaway for future multi-process vLLM VRAM budgeting on this host:**
|
||||||
|
do not just check "does it eventually come up" — check `NRestarts` and
|
||||||
|
free VRAM headroom after a clean stop/start. A model that "works" after
|
||||||
|
6 crash-loop retries is not production-stable; the retries themselves are
|
||||||
|
evidence the utilization ceiling is too tight for the actual (not
|
||||||
|
nominal) footprint of co-resident processes.
|
||||||
|
|
||||||
|
## Consumer cutover status (t_e6facb19, 2026-08-31)
|
||||||
|
|
||||||
|
**Attempted, then REVERTED — Hindsight LLM cutover.** Hindsight's
|
||||||
|
`HINDSIGHT_API_LLM_BASE_URL` was pointed at vLLM `:8000`
|
||||||
|
(Qwen2.5-32B-Instruct-AWQ) and validated working in isolation: health,
|
||||||
|
`/v1/chat/completions`, and a live `hindsight_retain` + recall round-trip
|
||||||
|
all succeeded (after also fixing `HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS`,
|
||||||
|
which defaulted to 64000 — exceeding vLLM's `max_model_len=8192` — down to
|
||||||
|
4096). **Reverted anyway**, because of a severe discovery documented in the
|
||||||
|
next section: vLLM cannot stay resident on this card without starving
|
||||||
|
llama-swap, and Hindsight's LLM endpoint needs continuous availability, not
|
||||||
|
just a validation window. Restored to `http://astro-orbiter:8001/v1`
|
||||||
|
(llama-swap, Qwen3.8-27B-Q4_K_M) — the pre-task working state.
|
||||||
|
|
||||||
|
**NOT cut over — embeddings.** Hindsight was discovered to have NEVER used
|
||||||
|
astro-orbiter for embeddings — it defaults to a bundled local
|
||||||
|
`BAAI/bge-small-en-v1.5` (384-dim) embedder whenever
|
||||||
|
`HINDSIGHT_API_EMBEDDINGS_PROVIDER` is unset, which was always the case here.
|
||||||
|
Pointing it at vLLM's `nomic-embed-text-v1.5` (768-dim) crash-looped the pod:
|
||||||
|
`RuntimeError: Cannot change embedding dimension from 384 to 768:
|
||||||
|
memory_units table contains 1289 rows with embeddings.` Re-embedding all
|
||||||
|
existing memory data across ~20 agent banks is destructive and irreversible
|
||||||
|
— reverted immediately, left as a separate, explicitly-approved future task.
|
||||||
|
|
||||||
|
**NOT cut over — 21 Hermes agent profiles' aux models + OpenViking VLM.**
|
||||||
|
See "Critical architectural finding" below — this was never attempted once
|
||||||
|
the VRAM collision was discovered, would have made things categorically
|
||||||
|
worse.
|
||||||
|
|
||||||
|
## Critical architectural finding: vLLM CANNOT be continuously resident alongside llama-swap on this 24GB card (t_e6facb19, 2026-08-31)
|
||||||
|
|
||||||
|
After validating vLLM's two processes (Qwen2.5-32B-Instruct-AWQ + nomic-embed-
|
||||||
|
text-v1.5, ~22.8GB combined) work correctly in isolation, this role's
|
||||||
|
`vllm_service_enabled`/`vllm_service_state` were flipped to `true`/`started`
|
||||||
|
as host_vars overrides to make the deployment permanent (per the task's
|
||||||
|
"enable for boot" requirement) — llama-swap was then restarted alongside
|
||||||
|
vLLM to preserve its own consumers. **Result: llama-swap could no longer
|
||||||
|
load ANY of its own generative models.** Every `/v1/chat/completions`
|
||||||
|
request against `Qwen3.8-27B-Q4_K_M` or the `Qwen3-8B` aux models failed
|
||||||
|
with `{"error":"unspecific error: upstream command exited prematurely",
|
||||||
|
"src":"llama-swap"}` — llama-server's own OOM at spawn time, only ~1.8GB
|
||||||
|
free on a 24GB card once vLLM's ~22.8GB was already claimed.
|
||||||
|
|
||||||
|
**Confirmed by direct A/B test, not inference:** identical
|
||||||
|
`Qwen3.8-27B-Q4_K_M` chat completion request returned HTTP 500 with vLLM's
|
||||||
|
two processes running, then HTTP 200 with a real completion within seconds
|
||||||
|
of `systemctl stop vllm.service vllm-nomic-embed-text-v1.5.service` — same
|
||||||
|
llama-swap process, same request, only the GPU memory pressure changed.
|
||||||
|
|
||||||
|
**This is a hard architectural collision, not a tunable-parameter problem.**
|
||||||
|
llama-swap needs ~18-20GB for its own primary model (Qwen3.8-27B-Q4_K_M);
|
||||||
|
vLLM's two processes need ~22.8GB even with `enforce_eager` and a lowered
|
||||||
|
`gpu_memory_utilization`. The two together need more VRAM than a 24GB card
|
||||||
|
has once both hold real models resident — there is no `gpu_memory_utilization`
|
||||||
|
value that resolves this while both stacks serve real production models
|
||||||
|
simultaneously.
|
||||||
|
|
||||||
|
**Consequence — reverted the boot-persistence flip.** `vllm_service_enabled`
|
||||||
|
and `vllm_service_state` are back to role defaults (`false`/`stopped`) in
|
||||||
|
`host_vars/astro-orbiter/vars.yml`. vLLM stays staged (venv, model weights,
|
||||||
|
systemd units all in place) and can be started for a brief shadow-validation
|
||||||
|
window (same pattern as t_ca1af9fb's original Phase 5), but is NOT safe to
|
||||||
|
leave resident in production alongside llama-swap.
|
||||||
|
|
||||||
|
**Path forward — requires a human decision, not more role tuning:**
|
||||||
|
1. Full llama-swap teardown (t_6dff1ecc) BEFORE vLLM gets permanent
|
||||||
|
residency — but that breaks the 21 agent profiles' aux-model tasks and
|
||||||
|
OpenViking's VLM unless those consumers are migrated to a different
|
||||||
|
backend first (Anthropic API, a second smaller local box, or a
|
||||||
|
redesigned single-process serving strategy that covers all the models
|
||||||
|
vLLM and llama-swap currently split between them).
|
||||||
|
2. Accept vLLM as a shadow-only / on-demand stack (manually started for
|
||||||
|
specific validated windows, stopped otherwise) and do NOT attempt
|
||||||
|
permanent Hindsight cutover — keeps llama-swap as the sole continuous
|
||||||
|
production serving layer, matching the pre-task state.
|
||||||
|
3. A hardware change (larger GPU, or a second GPU) — out of scope for this
|
||||||
|
task, flagging for Ryan's awareness if the aux-model consumer set is
|
||||||
|
expected to grow.
|
||||||
|
|
||||||
|
Comment posted on t_6dff1ecc with this finding — the teardown task remains
|
||||||
|
correctly blocked; this task's completion does NOT unblock it, because full
|
||||||
|
cutover to vLLM is not achievable within this card's VRAM budget as
|
||||||
|
currently scoped.
|
||||||
|
|
||||||
|
## RESOLVED (t_5508360a, 2026-08-31/09-01): Dashboard decision applied — llama-swap retired, vLLM permanent, 2 of 3 models
|
||||||
|
|
||||||
|
Human decision (dashboard, kanban t_5508360a): **"stop and disable llama-swap
|
||||||
|
and start vLLM and its 3 models"** — explicit approval, "I understand this is
|
||||||
|
a breaking change." Chose path 1 from the three options above: retire
|
||||||
|
llama-swap, give vLLM permanent residency, accept that the 21 Hermes
|
||||||
|
profiles' aux-model consumers lose their llama-swap aux roster (Qwen3-8B,
|
||||||
|
Phi-3.5-mini, Meta-Llama-3.1-8B, Qwen2.5-Coder-14B — all 4 gone) in exchange
|
||||||
|
for vLLM's stack. Mid-run the dashboard added a course-correction: **"Don't
|
||||||
|
try to load all 3 models concurrently on first deploy. Start with
|
||||||
|
Qwen2.5-32B only"** — received after the 3-model attempt below had already
|
||||||
|
run and self-corrected to the same 2-model end state, so no further action
|
||||||
|
needed, but noted for the record.
|
||||||
|
|
||||||
|
**Executed:**
|
||||||
|
1. `sudo systemctl stop llama-swap && sudo systemctl disable llama-swap` on
|
||||||
|
astro-orbiter — confirmed inactive+disabled, VRAM dropped to 9MiB/24576MiB
|
||||||
|
(from 20.6GB in production use).
|
||||||
|
2. Flipped `vllm_service_enabled`/`vllm_service_state` to `true`/`started` in
|
||||||
|
`host_vars/astro-orbiter/vars.yml` — vLLM is now the permanent,
|
||||||
|
boot-persistent serving layer (was shadow-only/staged before this task).
|
||||||
|
3. **Attempted the literal "3 models" instruction** — flipped
|
||||||
|
`Qwen3-8B-AWQ.enabled` to `true` too. **Does not fit.** With the 24GB
|
||||||
|
card's usable 23.55GiB budget consumed by Qwen2.5-32B-Instruct-AWQ
|
||||||
|
(~18.6GB weights) + nomic-embed-text-v1.5 (~0.8GB actual), only ~1.25GiB
|
||||||
|
remained free — below the 3.53GiB floor `gpu_memory_utilization=0.15`
|
||||||
|
requires for Qwen3-8B-AWQ even with `enforce_eager`. Confirmed via
|
||||||
|
`journalctl`: identical `ValueError: Free memory on device cuda:0
|
||||||
|
(1.25/23.55 GiB) on startup is less than desired GPU memory utilization`
|
||||||
|
on all 7 consecutive systemd restart attempts — not the transient
|
||||||
|
CUDA-graph-capture crash-loop t_e6facb19 solved with enforce_eager, a hard
|
||||||
|
ceiling. Stopped + disabled `vllm-Qwen3-8B-AWQ.service`, reverted
|
||||||
|
`enabled: false` in host_vars with a full writeup in the comment block.
|
||||||
|
4. Re-ran `day1_deploy_vllm.yml --extra-vars vllm_service_state=started`
|
||||||
|
with the corrected 2-model config: **clean idempotent pass, changed=0** on
|
||||||
|
both remaining models, Phase 5 verification passed (`/health` 200 on both
|
||||||
|
`:8000` and `:8020`, `/v1/models` correct, live completion + live
|
||||||
|
embeddings smoke tests both passed), `NRestarts=0` on both services.
|
||||||
|
5. **Cut over Hindsight's LLM endpoint** (the other production consumer):
|
||||||
|
`HINDSIGHT_API_LLM_BASE_URL` llama-swap `:8001` → vLLM `:8000`,
|
||||||
|
`HINDSIGHT_API_LLM_MODEL` → `Qwen2.5-32B-Instruct-AWQ`, added
|
||||||
|
`HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS=4096` (vLLM's
|
||||||
|
`max_model_len=8192` vs Hindsight's 64000 default), and switched the
|
||||||
|
ExternalSecret's `HINDSIGHT_API_LLM_API_KEY` source from the unused
|
||||||
|
`nous` 1Password item to `vllm`'s real `api-key` (vLLM validates its
|
||||||
|
bearer token; llama-swap never did). Committed to
|
||||||
|
`cluster/applications/hindsight/{values.yaml,externalsecret.yaml}`,
|
||||||
|
pushed, ArgoCD synced, confirmed the new pod logged `Connection verified:
|
||||||
|
openai/Qwen2.5-32B-Instruct-AWQ` on boot.
|
||||||
|
6. **Live end-to-end verification**, not inference: a real
|
||||||
|
`POST /v1/default/banks/war-machine/memories` retain call against the
|
||||||
|
production Hindsight endpoint returned `HTTP 200` with genuine
|
||||||
|
fact-extraction token usage (3257 in / 245 out), and a subsequent
|
||||||
|
`POST .../memories/recall` returned real semantically-ranked results
|
||||||
|
including the just-retained memory.
|
||||||
|
|
||||||
|
**Final production state on astro-orbiter (verified live):**
|
||||||
|
- `vllm.service` (Qwen2.5-32B-Instruct-AWQ, :8000): active, enabled, boot-persistent
|
||||||
|
- `vllm-nomic-embed-text-v1.5.service` (:8020): active, enabled, boot-persistent
|
||||||
|
- `vllm-Qwen3-8B-AWQ.service` (:8010): inactive, disabled — does not fit, see above
|
||||||
|
- `llama-swap.service`: inactive, disabled (unit files left in place —
|
||||||
|
full removal is t_6dff1ecc's job, tracked separately)
|
||||||
|
- VRAM: ~22.6GB/24.576GB in steady-state use, no crash-looping
|
||||||
|
|
||||||
|
**What this means for t_6dff1ecc (teardown) and the 21 aux-model profiles:**
|
||||||
|
llama-swap is now stopped+disabled — t_6dff1ecc's actual teardown steps
|
||||||
|
(remove systemd unit files, wipe caches) are now safe to execute and
|
||||||
|
unblocked from a "live production" standpoint. However, this trades away
|
||||||
|
the aux-model roster: the 21 Hermes profiles' aux-model tasks (skills_hub,
|
||||||
|
approval, mcp, title_generation, profile_describer, compression) that
|
||||||
|
used to route to llama-swap's Qwen3-8B/Phi-3.5-mini/Meta-Llama/Coder
|
||||||
|
models now have **zero local aux-model backend** — Qwen3-8B-AWQ doesn't
|
||||||
|
fit vLLM's VRAM budget either. This was accepted explicitly by the
|
||||||
|
dashboard ("I understand this is a breaking change") — no further local
|
||||||
|
aux-model migration was authorized or attempted in this task. If those 21
|
||||||
|
profiles need a replacement aux-model path, that is separate, new,
|
||||||
|
explicitly-scoped follow-up work, not implied by this decision.
|
||||||
|
|
||||||
|
## SUPERSEDED (t_r1d32b_swap, 2026-09-01): Qwen2.5-32B-Instruct-AWQ retired, replaced with DeepSeek-R1-Distill-Qwen-32B-AWQ, single-model deployment
|
||||||
|
|
||||||
|
Ryan direction: "Swap Qwen2.5-32B for DeepSeek-R1-Distill-Qwen-32B,
|
||||||
|
max-model-len 32768. Single model only." Confirmed with Ryan that "single
|
||||||
|
model only" includes disabling `nomic-embed-text-v1.5` (:8020) as well —
|
||||||
|
nothing in production consumed it (Hindsight uses its own bundled 384-dim
|
||||||
|
embedder; OpenViking pointed at the retired llama-swap endpoint). DeepSeek
|
||||||
|
gets the entire 24GB card.
|
||||||
|
|
||||||
|
**Model choice:** `casperhansen/deepseek-r1-distill-qwen-32b-awq` — same
|
||||||
|
AutoAWQ toolchain/quant style as the outgoing Qwen2.5-32B-Instruct-AWQ,
|
||||||
|
widely-used community quant, `Qwen2ForCausalLM` architecture (DeepSeek-R1
|
||||||
|
reasoning distilled onto a Qwen2.5-32B base) — no new vLLM code path
|
||||||
|
required. Native `max_position_embeddings: 131072`; capped at 32768 per
|
||||||
|
the task's explicit requirement.
|
||||||
|
|
||||||
|
**Executed:**
|
||||||
|
1. Stopped + disabled `vllm-nomic-embed-text-v1.5.service` (single-model
|
||||||
|
requirement), freed its ~19GB Qwen2.5-32B model cache on disk (30GB
|
||||||
|
free → 48GB free) to make room for DeepSeek's ~19.3GB download.
|
||||||
|
2. Replaced `vllm_models` in `host_vars/astro-orbiter/vars.yml`: primary
|
||||||
|
entry now `DeepSeek-R1-Distill-Qwen-32B-AWQ`, aux (`Qwen3-8B-AWQ`) and
|
||||||
|
embedding (`nomic-embed-text-v1.5`) both `enabled: false`.
|
||||||
|
3. Staged the model via `--tags vllm-models` (idempotent `hf download`,
|
||||||
|
~19GB, confirmed via `du -sh` and snapshot-dir stat).
|
||||||
|
4. **Three rounds of live VRAM-fit debugging** before a stable config was
|
||||||
|
found (documented inline in host_vars comments) — worth recording here
|
||||||
|
since the failure mode is non-obvious and will recur for future
|
||||||
|
32B-class models at high context on this 24GB card:
|
||||||
|
- **Round 1 (fp16 KV, gpu_memory_utilization 0.90/0.95/0.98):** vLLM's
|
||||||
|
own pre-flight check reported 18.17GiB weights + 8.0GiB KV cache
|
||||||
|
needed at 32768 ctx fp16 = 26.17GB — mathematically impossible on a
|
||||||
|
24GB card at ANY utilization percentage. Crash-looped every attempt.
|
||||||
|
- **Round 2 (`--kv-cache-dtype fp8`):** halved nominal KV cache to
|
||||||
|
~4.0-4.3GiB, should fit with ~1GB margin. Still OOM'd — small
|
||||||
|
(~50-150MB) `cudaMalloc` failures during FlashInfer kernel warmup,
|
||||||
|
consistently, even when vLLM's own pre-flight math said it should
|
||||||
|
fit. Root cause: real GPU usage during warmup kernel compilation
|
||||||
|
exceeds what upfront profiling/reservation accounts for by roughly
|
||||||
|
~1GB (unaccounted FlashInfer/sampler warmup workspace buffers).
|
||||||
|
Tried both the percentage knob AND vLLM's own suggested
|
||||||
|
`--kv-cache-memory-bytes` exact value — same failure either way,
|
||||||
|
confirming the gap wasn't a rounding/estimation error in the
|
||||||
|
percentage math, it was a real missing ~1GB of margin.
|
||||||
|
- **Round 3 (`--kv-cache-dtype int4_per_token_head`, fixed): SUCCESS.**
|
||||||
|
Switching from 8-bit to 4-bit KV cache roughly halves the KV
|
||||||
|
footprint again (~2GiB instead of ~4-4.3GiB), buying back enough
|
||||||
|
real headroom to absorb the unaccounted warmup overhead. Clean
|
||||||
|
single-attempt start, `NRestarts=0`, steady-state VRAM 23.2GB/24.576GB.
|
||||||
|
5. **Full Ansible verify phase (`--tags vllm-api-key,vllm-verify`)**
|
||||||
|
passed: systemd unit active, `/health` 200, `/v1/models` returns
|
||||||
|
`DeepSeek-R1-Distill-Qwen-32B-AWQ` with `max_model_len: 32768`, live
|
||||||
|
`/v1/completions` smoke test HTTP 200, clean restart + re-run of
|
||||||
|
`--tags vllm-systemd` confirmed idempotent (`changed=0`,
|
||||||
|
`NRestarts=0`, same `ActiveEnterTimestamp` — no unnecessary restart).
|
||||||
|
6. **Manual end-to-end generation test**, not inference: a real
|
||||||
|
`/v1/chat/completions` call ("What is 12*8?") returned a genuine
|
||||||
|
DeepSeek-R1 reasoning trace in `<think>` tags followed by the correct
|
||||||
|
answer (96) with correct step-by-step arithmetic shown — confirms the
|
||||||
|
model is not just health-check-alive but actually reasoning correctly.
|
||||||
|
|
||||||
|
**Role/template changes (reusable for future models on this host):**
|
||||||
|
- Added `kv_cache_dtype` (renders `--kv-cache-dtype`) and
|
||||||
|
`kv_cache_memory_bytes` (renders `--kv-cache-memory-bytes`) as new
|
||||||
|
optional per-model fields in `vllm.service.j2` — both are `{% if
|
||||||
|
... is defined %}` guarded, no effect on models that don't set them.
|
||||||
|
|
||||||
|
**Final production state on astro-orbiter (verified live, 2026-09-01):**
|
||||||
|
- `vllm.service` (DeepSeek-R1-Distill-Qwen-32B-AWQ, :8000, `max_model_len:
|
||||||
|
32768`, `kv_cache_dtype: int4_per_token_head`): active, enabled,
|
||||||
|
boot-persistent, single model on the card
|
||||||
|
- `vllm-nomic-embed-text-v1.5.service` (:8020): inactive, disabled
|
||||||
|
- `vllm-Qwen3-8B-AWQ.service` (:8010): inactive, disabled (unchanged from prior state)
|
||||||
|
- `llama-swap.service`: inactive, disabled (unchanged from prior state)
|
||||||
|
- VRAM: ~23.2GB/24.576GB steady-state, no crash-looping, `NRestarts=0`
|
||||||
|
|
||||||
|
**Not done in this task (flagging, not implied by this swap):**
|
||||||
|
- Hindsight's `HINDSIGHT_API_LLM_MODEL` / `HINDSIGHT_API_LLM_BASE_URL`
|
||||||
|
cluster config still references `Qwen2.5-32B-Instruct-AWQ` — that model
|
||||||
|
is now gone from the card. Hindsight's LLM calls to astro-orbiter will
|
||||||
|
fail model-not-found until that GitOps config is updated to point at
|
||||||
|
`DeepSeek-R1-Distill-Qwen-32B-AWQ`. Not touched here — task scope was
|
||||||
|
the astro-orbiter model swap itself, cluster consumer cutover is a
|
||||||
|
separate, explicit follow-up (same boundary respected in the prior
|
||||||
|
t_5508360a section: this role does not own cluster-side config).
|
||||||
|
- DeepSeek-R1's reasoning output uses `<think>` tags and the model card
|
||||||
|
recommends temperature 0.5-0.7 (not greedy/0) — neither is enforced
|
||||||
|
server-side; any consumer wiring this model into a Hermes profile or
|
||||||
|
application should account for both when parsing responses.
|
||||||
|
|
||||||
|
## Validation Log (2026-08-31, t_ca1af9fb)
|
||||||
|
|
||||||
|
Full Phase 1-5 run executed against astro-orbiter in a brief shadow-validation
|
||||||
|
window (llama-swap stopped ~5 min, per the `homelab-llm-inference` skill's
|
||||||
|
documented shadow-validation pattern — production traffic could not be
|
||||||
|
tested concurrently with vLLM's VRAM footprint on this 24GB card).
|
||||||
|
|
||||||
|
**Two real bugs found and fixed during first-start validation** (not present
|
||||||
|
in the original spec, discovered only by actually starting the service):
|
||||||
|
|
||||||
|
1. **`ninja` not on systemd's PATH.** vLLM's torch.compile path shells out to
|
||||||
|
the bare `ninja` command. `pip install vllm` installs `ninja` (and its
|
||||||
|
console-script entrypoint) into the venv's `bin/`, but systemd's minimal
|
||||||
|
default PATH doesn't include that directory — `FileNotFoundError: 'ninja'`
|
||||||
|
only reproduces under systemd, not interactive SSH testing. Fixed by
|
||||||
|
setting `Environment="PATH=<venv>/bin:...standard dirs..."` in the unit
|
||||||
|
template.
|
||||||
|
2. **FlashInfer sampler JIT fails to compile on RTX 3090 (SM86).**
|
||||||
|
`flashinfer/data/csrc/sampling.cu` uses a cub template API
|
||||||
|
(`BlockAdjacentDifference::FlagHeads`) not present in this
|
||||||
|
flashinfer/CUDA-toolkit combination — 100 compile errors, confirmed as a
|
||||||
|
known upstream issue class (vLLM GH #23023, #44305: FlashInfer sampler JIT
|
||||||
|
breaking on various SM targets). Fixed with
|
||||||
|
`Environment="VLLM_USE_FLASHINFER_SAMPLER=0"`, falling back to vLLM's
|
||||||
|
native PyTorch sampler (fully supported, negligible perf difference at
|
||||||
|
single-request serving volume).
|
||||||
|
|
||||||
|
Also corrected `vllm_gpu_memory_utilization` from 0.90 to 0.95 — at 0.90 the
|
||||||
|
KV cache allocation failed (`2.0 GiB KV cache needed, 1.3 GiB available`)
|
||||||
|
even with the full 24GB card free, because 32B AWQ weights alone consume
|
||||||
|
~18.4GB, leaving too little headroom at a 90% cap.
|
||||||
|
|
||||||
|
**Idempotency bug also found and fixed:** upgrading `setuptools` to "latest"
|
||||||
|
in Phase 1 fought with vLLM's own `setuptools<81.0.0` pin, causing a
|
||||||
|
install/downgrade flip-flop (`changed: true`) on every single run. Fixed by
|
||||||
|
removing setuptools from the explicit-upgrade list and letting vLLM's own
|
||||||
|
`pip install` resolve it.
|
||||||
|
|
||||||
|
**Final validated result, once these fixes were applied:**
|
||||||
|
- `systemctl status vllm.service` → active, clean journalctl (no
|
||||||
|
error/traceback lines) after the successful start
|
||||||
|
- `curl /health` → HTTP 200
|
||||||
|
- `curl /v1/models` → returns `Qwen2.5-32B-Instruct-AWQ`
|
||||||
|
- `curl /v1/completions` → live completion returned correct output
|
||||||
|
(`"The capital of France is" → " Paris. Correct! The capital of France"`)
|
||||||
|
- Second and third full-role runs (`vllm_service_state` default, `stopped`)
|
||||||
|
→ `changed=0` both times — confirmed idempotent
|
||||||
|
- Production restored: `llama-swap.service` active, `/health` 200,
|
||||||
|
`/v1/embeddings` against `nomic-embed-text-v1.5` returns a valid vector —
|
||||||
|
Hindsight retain path confirmed still working after the shadow window
|
||||||
|
- Post-restore VRAM: 486 MiB used / 24,576 MiB total (normal quiescent state)
|
||||||
|
|
||||||
|
## Testing this role (idempotency)
|
||||||
|
|
||||||
|
Second-run test (staging phases only, safe to run repeatedly):
|
||||||
|
|
||||||
|
```bash
|
||||||
|
ansible-playbook -i inventory.yml playbooks/day1_deploy_vllm.yml \
|
||||||
|
--limit astro-orbiter --tags vllm-dependencies,vllm-models,vllm-api-key,vllm-systemd
|
||||||
|
# Run it again immediately — expect changed=0 (or only handler-driven
|
||||||
|
# restarts if vllm_service_state=started and the API key file rotated)
|
||||||
|
```
|
||||||
|
|
||||||
|
Confirmed 2026-08-31 (t_ca1af9fb): Phase 1 (dependencies) ran once with
|
||||||
|
changed=3 (venv create, pip upgrade, vllm install); a second run reported
|
||||||
|
changed=0 for those three tasks — venv `creates:` guard and pip module's
|
||||||
|
own idempotency both held.
|
||||||
|
|
||||||
|
## Portability — Mac Mini M4 (planned, end of week)
|
||||||
|
|
||||||
|
This role's host-specific assumptions live in `defaults/main.yml` (all
|
||||||
|
overridable via `host_vars/<host>/vars.yml`) plus one hard assumption baked
|
||||||
|
into `tasks/dependencies.yml`: an NVIDIA GPU (`nvidia-smi` check, CUDA
|
||||||
|
wheels). Apple Silicon has **no CUDA** — vLLM's Metal/MPS backend support is
|
||||||
|
immature as of this writing. Before reusing this role for the Mac Mini M4:
|
||||||
|
|
||||||
|
1. Fork `tasks/dependencies.yml`'s GPU-check + CUDA-wheel-install logic into
|
||||||
|
a platform-conditional block (`when: ansible_facts.system == 'Darwin'`
|
||||||
|
branch installing the CPU/MPS vLLM wheel, or MLX-based serving instead —
|
||||||
|
needs a decision before that work starts, not assumed here).
|
||||||
|
2. `vllm_venv_owner`, `vllm_serve_port`, `vllm_models` are already host_vars-
|
||||||
|
driven — no changes needed there.
|
||||||
|
3. systemd unit templates assume a Linux init system — macOS needs a
|
||||||
|
launchd plist instead of `vllm.service.j2`.
|
||||||
|
|
||||||
|
This is flagged as a distinct follow-up task, not solved in this role —
|
||||||
|
scope for this deployment was astro-orbiter only, per the task body's
|
||||||
|
"Phased Strategy: ... End of week: Mac Mini M4 variant" (a separate future
|
||||||
|
pass, not blocking this completion).
|
||||||
|
|
||||||
|
## Files
|
||||||
|
|
||||||
|
```
|
||||||
|
roles/deploy-vllm/
|
||||||
|
├── defaults/main.yml # all tunables — host overrides go in host_vars
|
||||||
|
├── handlers/main.yml # reload systemd / restart vllm services
|
||||||
|
├── meta/main.yml
|
||||||
|
├── tasks/
|
||||||
|
│ ├── main.yml # phase orchestrator
|
||||||
|
│ ├── dependencies.yml # Phase 1
|
||||||
|
│ ├── models.yml # Phase 2
|
||||||
|
│ ├── api-key.yml # Phase 3
|
||||||
|
│ ├── systemd.yml # Phase 4
|
||||||
|
│ └── verify.yml # Phase 5
|
||||||
|
├── templates/
|
||||||
|
│ ├── vllm.service.j2 # one instance per enabled model
|
||||||
|
│ └── vllm-workspace.sh.j2 # debugging helper deployed to the target
|
||||||
|
└── README.md # this file
|
||||||
|
```
|
||||||
@@ -0,0 +1,91 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/defaults/main.yml
|
||||||
|
# ROLE: deploy-vllm — vLLM OpenAI-compatible serving stack
|
||||||
|
# DESIGNED FOR REUSE: astro-orbiter (RTX 3090, 24GB) today, Mac Mini M4 later.
|
||||||
|
# Host-specific values (VRAM budget, model list, ports) belong in host_vars,
|
||||||
|
# not here. These are the safe, conservative defaults.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
# --- Python / venv -----------------------------------------------------------
|
||||||
|
vllm_venv_owner: jarvis
|
||||||
|
vllm_venv_path: "/home/{{ vllm_venv_owner }}/vllm-serve-env"
|
||||||
|
vllm_python_min_version: "3.10"
|
||||||
|
vllm_version_spec: "vllm>=0.5.0"
|
||||||
|
|
||||||
|
# --- Model cache ---------------------------------------------------------
|
||||||
|
vllm_cache_dir: "/home/{{ vllm_venv_owner }}/.vllm-cache"
|
||||||
|
vllm_hf_hub_cache: "{{ vllm_cache_dir }}/huggingface"
|
||||||
|
|
||||||
|
# --- Serving ---------------------------------------------------------------
|
||||||
|
vllm_serve_host: "0.0.0.0"
|
||||||
|
vllm_serve_port: 8000
|
||||||
|
vllm_gpu_memory_utilization: 0.95
|
||||||
|
vllm_max_model_len: 8192
|
||||||
|
vllm_dtype: "auto"
|
||||||
|
|
||||||
|
# --- Models --------------------------------------------------------------
|
||||||
|
# Each entry: id (served --model / OpenAI "model" field), hf_repo, role
|
||||||
|
# (primary/aux/embedding), quantization, and per-model overrides.
|
||||||
|
# Only models with enabled: true are staged + wired into the systemd unit's
|
||||||
|
# --model roster consideration. vLLM 0.5.x serves ONE model per process, so
|
||||||
|
# multi-model = multiple systemd instances (see vllm_instances below) or a
|
||||||
|
# router in front (out of scope for this role — matches the astro-orbiter
|
||||||
|
# phased plan: Qwen2.5-32B today, add Qwen3-8B + embedding later).
|
||||||
|
vllm_models:
|
||||||
|
- id: "Qwen2.5-32B-Instruct-AWQ"
|
||||||
|
hf_repo: "Qwen/Qwen2.5-32B-Instruct-AWQ"
|
||||||
|
role: primary
|
||||||
|
quantization: awq
|
||||||
|
port: 8000
|
||||||
|
max_model_len: "{{ vllm_max_model_len }}"
|
||||||
|
gpu_memory_utilization: "{{ vllm_gpu_memory_utilization }}"
|
||||||
|
enabled: true
|
||||||
|
- id: "Qwen3-8B-AWQ"
|
||||||
|
hf_repo: "Qwen/Qwen3-8B-AWQ"
|
||||||
|
role: aux
|
||||||
|
quantization: awq
|
||||||
|
port: 8010
|
||||||
|
max_model_len: 32768
|
||||||
|
gpu_memory_utilization: 0.15
|
||||||
|
enabled: false
|
||||||
|
- id: "nomic-embed-text-v1.5"
|
||||||
|
hf_repo: "nomic-ai/nomic-embed-text-v1.5"
|
||||||
|
role: embedding
|
||||||
|
quantization: none
|
||||||
|
port: 8020
|
||||||
|
max_model_len: 2048
|
||||||
|
gpu_memory_utilization: 0.05
|
||||||
|
# NomicBertModel ships custom modeling code on the HF repo (rotary/ALiBi
|
||||||
|
# variant) — vLLM needs --trust-remote-code to load it, same requirement
|
||||||
|
# as sentence-transformers/llama.cpp. Wired into vllm.service.j2 (t_e6facb19).
|
||||||
|
trust_remote_code: true
|
||||||
|
enabled: false
|
||||||
|
|
||||||
|
# --- systemd ---------------------------------------------------------------
|
||||||
|
vllm_service_name: vllm
|
||||||
|
vllm_service_state: stopped # deliberate: role stages everything but does NOT
|
||||||
|
# flip production traffic. Cutover is a separate,
|
||||||
|
# explicitly-approved step (see README.md).
|
||||||
|
vllm_service_enabled: false # deliberate: do NOT enable for boot by default.
|
||||||
|
# llama-swap is live production on this GPU —
|
||||||
|
# enabling vllm.service means a host reboot would
|
||||||
|
# auto-start it and immediately VRAM-collide with
|
||||||
|
# llama-swap (confirmed failure mode during Phase 5
|
||||||
|
# validation, t_ca1af9fb 2026-08-31). Flip to true
|
||||||
|
# only as part of the deliberate cutover step,
|
||||||
|
# together with tearing down llama-swap.
|
||||||
|
vllm_restart_policy: always
|
||||||
|
|
||||||
|
# --- API key -----------------------------------------------------------
|
||||||
|
# Source of truth: 1Password op://mk-labs/vllm/api-key (Nick Fury manages).
|
||||||
|
# This role does NOT generate a key by default — it expects one to already
|
||||||
|
# exist in 1Password and reads it via `op read` at deploy time (delegate_to
|
||||||
|
# localhost, where the op CLI is authenticated). Set vllm_generate_api_key
|
||||||
|
# to true only for first-ever bootstrap when no 1Password item exists yet.
|
||||||
|
vllm_generate_api_key: false
|
||||||
|
vllm_api_key_op_ref: "op://mk-labs/vllm/api-key"
|
||||||
|
vllm_api_key_env_file: "/etc/vllm/api-key.env"
|
||||||
|
|
||||||
|
# --- Verification ------------------------------------------------------
|
||||||
|
vllm_health_check_retries: 30
|
||||||
|
vllm_health_check_delay: 10
|
||||||
@@ -0,0 +1,18 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/handlers/main.yml
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: reload systemd
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
daemon_reload: true
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: restart vllm services
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: "{{ 'vllm.service' if item.role == 'primary' else 'vllm-' + item.id + '.service' }}"
|
||||||
|
state: restarted
|
||||||
|
loop: "{{ vllm_enabled_models | default([]) }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
become: true
|
||||||
|
when: vllm_service_state == 'started'
|
||||||
@@ -0,0 +1,17 @@
|
|||||||
|
---
|
||||||
|
galaxy_info:
|
||||||
|
role_name: deploy_vllm
|
||||||
|
author: War Machine (MLOps & Inference Serving Specialist)
|
||||||
|
description: >-
|
||||||
|
Idempotent vLLM OpenAI-compatible serving stack deployment. Designed for
|
||||||
|
reuse across GPU hosts (astro-orbiter RTX 3090 today, Mac Mini M4 planned
|
||||||
|
end-of-week variant). Phased: dependencies -> models -> api-key -> systemd
|
||||||
|
-> verify.
|
||||||
|
license: internal (mk-labs homelab, not for external distribution)
|
||||||
|
min_ansible_version: "2.14"
|
||||||
|
platforms:
|
||||||
|
- name: Ubuntu
|
||||||
|
versions:
|
||||||
|
- jammy
|
||||||
|
- noble
|
||||||
|
dependencies: []
|
||||||
@@ -0,0 +1,112 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/tasks/api-key.yml
|
||||||
|
# PHASE 3: API key management.
|
||||||
|
#
|
||||||
|
# Source of truth: 1Password op://mk-labs/vllm/api-key (Nick Fury manages).
|
||||||
|
# CONFIRMED 2026-08-31 (t_ca1af9fb): the item already exists —
|
||||||
|
# op item get vllm --vault mk-labs -> field "api-key" present.
|
||||||
|
# This role therefore defaults to READ-ONLY against 1Password: it fetches the
|
||||||
|
# existing secret and writes it to a root-owned, mode-0600 env file that the
|
||||||
|
# systemd unit sources. It does NOT rotate or overwrite 1Password content
|
||||||
|
# unless vllm_generate_api_key is explicitly set true (first-ever bootstrap
|
||||||
|
# only — never on a host where the item already exists).
|
||||||
|
#
|
||||||
|
# `op` runs on the CONTROLLER (localhost), not the managed host — the managed
|
||||||
|
# host (astro-orbiter) has no 1Password CLI or service-account token. The
|
||||||
|
# resolved secret is pushed to the host via `ansible.builtin.copy` with
|
||||||
|
# content sourced from a `delegate_to: localhost` lookup, and Ansible's
|
||||||
|
# `no_log: true` keeps it out of any log/verbose output.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: "Generate a new API key (BOOTSTRAP ONLY, vllm_generate_api_key=true)"
|
||||||
|
ansible.builtin.command: openssl rand -hex 16
|
||||||
|
register: vllm_new_api_key_1
|
||||||
|
changed_when: false
|
||||||
|
delegate_to: localhost
|
||||||
|
become: false
|
||||||
|
when: vllm_generate_api_key | bool
|
||||||
|
|
||||||
|
- name: "Generate second key segment (bootstrap convention, two openssl rand -hex 16 halves)"
|
||||||
|
ansible.builtin.command: openssl rand -hex 16
|
||||||
|
register: vllm_new_api_key_2
|
||||||
|
changed_when: false
|
||||||
|
delegate_to: localhost
|
||||||
|
become: false
|
||||||
|
when: vllm_generate_api_key | bool
|
||||||
|
|
||||||
|
- name: Store newly generated key in 1Password (bootstrap only)
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: >-
|
||||||
|
op item create --category=SERVER --title=vllm --vault=mk-labs
|
||||||
|
"api-key[password]={{ vllm_new_api_key_1.stdout }}{{ vllm_new_api_key_2.stdout }}"
|
||||||
|
delegate_to: localhost
|
||||||
|
become: false
|
||||||
|
when: vllm_generate_api_key | bool
|
||||||
|
no_log: true
|
||||||
|
|
||||||
|
- name: Read the vLLM API key from 1Password
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "op read '{{ vllm_api_key_op_ref }}'"
|
||||||
|
register: vllm_api_key_lookup
|
||||||
|
delegate_to: localhost
|
||||||
|
become: false
|
||||||
|
changed_when: false
|
||||||
|
no_log: true
|
||||||
|
|
||||||
|
- name: Fail if the 1Password lookup returned nothing
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: >-
|
||||||
|
op read {{ vllm_api_key_op_ref }} returned an empty value. Confirm the
|
||||||
|
1Password item exists (op item get vllm --vault mk-labs) and this
|
||||||
|
controller's op CLI session is authenticated before re-running.
|
||||||
|
when: vllm_api_key_lookup.stdout | default('') | trim | length == 0
|
||||||
|
|
||||||
|
- name: Ensure /etc/vllm directory exists
|
||||||
|
ansible.builtin.file:
|
||||||
|
path: "{{ vllm_api_key_env_file | dirname }}"
|
||||||
|
state: directory
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0750"
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Write API key env file (root-owned, 0600, not world-readable)
|
||||||
|
ansible.builtin.copy:
|
||||||
|
dest: "{{ vllm_api_key_env_file }}"
|
||||||
|
content: "VLLM_API_KEY={{ vllm_api_key_lookup.stdout }}\n"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0600"
|
||||||
|
become: true
|
||||||
|
no_log: true
|
||||||
|
notify: restart vllm services
|
||||||
|
|
||||||
|
- name: Record quarterly rotation reminder doc (idempotent, content-driven)
|
||||||
|
ansible.builtin.copy:
|
||||||
|
dest: "/etc/vllm/API_KEY_ROTATION.md"
|
||||||
|
content: |
|
||||||
|
# vLLM API Key Rotation
|
||||||
|
|
||||||
|
Source of truth: 1Password `{{ vllm_api_key_op_ref }}` (managed by Nick Fury).
|
||||||
|
|
||||||
|
## Rotation procedure (target: quarterly)
|
||||||
|
|
||||||
|
1. Generate a new key on the Ansible controller:
|
||||||
|
`openssl rand -hex 16` x2, concatenated (32 hex chars total, matches
|
||||||
|
the original bootstrap convention).
|
||||||
|
2. Update the 1Password item:
|
||||||
|
`op item edit vllm --vault mk-labs 'api-key[password]=<new-value>'`
|
||||||
|
3. Re-run this role (`ansible-playbook ... --tags vllm-api-key,vllm-systemd`)
|
||||||
|
to push the new key to /etc/vllm/api-key.env and restart the vllm
|
||||||
|
service(s) with the new key.
|
||||||
|
4. Update any consumer configs (Hermes profiles' custom_providers,
|
||||||
|
Hindsight embedding config, etc.) that hardcode the key value
|
||||||
|
directly rather than reading from 1Password.
|
||||||
|
5. Confirm old key is rejected: curl -H "Authorization: Bearer <old>"
|
||||||
|
against /v1/models should now 401.
|
||||||
|
|
||||||
|
Last rotated: see 1Password item audit log (op item get vllm --vault mk-labs).
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
become: true
|
||||||
@@ -0,0 +1,113 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/tasks/dependencies.yml
|
||||||
|
# PHASE 1: Python 3.10+, vLLM >=0.5.0, PyTorch+CUDA, verify nvidia-smi.
|
||||||
|
#
|
||||||
|
# Pitfall (homelab-llm-serving skill): vLLM bundles its own CUDA 12.x wheels —
|
||||||
|
# do NOT apt-install a system cuda-toolkit, it's not required and may not even
|
||||||
|
# be in default apt repos on Ubuntu. pip install vllm is sufficient.
|
||||||
|
#
|
||||||
|
# Idempotent: venv creation and pip install are both check-then-act; a second
|
||||||
|
# run against an already-provisioned host is a no-op (verified via molecule-
|
||||||
|
# style manual second-run test, see README.md Testing section).
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Verify nvidia-smi is present and a GPU is visible
|
||||||
|
ansible.builtin.command: nvidia-smi --query-gpu=name,memory.total,driver_version --format=csv,noheader
|
||||||
|
register: vllm_nvidia_smi
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: Report detected GPU
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "GPU detected: {{ vllm_nvidia_smi.stdout }}"
|
||||||
|
|
||||||
|
- name: Fail fast if nvidia-smi reports no GPU
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "nvidia-smi returned no GPU rows — cannot deploy vLLM without a CUDA-visible GPU."
|
||||||
|
when: vllm_nvidia_smi.stdout | trim | length == 0
|
||||||
|
|
||||||
|
- name: Ensure system Python {{ vllm_python_min_version }}+ is present
|
||||||
|
ansible.builtin.command: "python3 -c 'import sys; assert sys.version_info >= (3, 10), sys.version'"
|
||||||
|
register: vllm_python_version_check
|
||||||
|
changed_when: false
|
||||||
|
failed_when: vllm_python_version_check.rc != 0
|
||||||
|
|
||||||
|
- name: Ensure python3-venv is installed
|
||||||
|
ansible.builtin.apt:
|
||||||
|
name: python3-venv
|
||||||
|
state: present
|
||||||
|
update_cache: true
|
||||||
|
cache_valid_time: 3600
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Create dedicated vLLM Python venv
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "python3 -m venv {{ vllm_venv_path }}"
|
||||||
|
creates: "{{ vllm_venv_path }}/bin/python"
|
||||||
|
become: true
|
||||||
|
become_user: "{{ vllm_venv_owner }}"
|
||||||
|
|
||||||
|
- name: Upgrade pip/wheel inside the venv
|
||||||
|
ansible.builtin.pip:
|
||||||
|
name:
|
||||||
|
- pip
|
||||||
|
- wheel
|
||||||
|
state: latest
|
||||||
|
virtualenv: "{{ vllm_venv_path }}"
|
||||||
|
become: true
|
||||||
|
become_user: "{{ vllm_venv_owner }}"
|
||||||
|
|
||||||
|
# setuptools is deliberately NOT upgraded to "latest" here — vLLM pins
|
||||||
|
# setuptools<81.0.0,>=77.0.3 as a transitive dependency. Forcing it to latest
|
||||||
|
# (84.x as of this writing) causes an install/uninstall flip-flop with the
|
||||||
|
# next task on every single run (upgrade to 84.x here, vLLM's pip install
|
||||||
|
# downgrades it back to satisfy its own pin) — a genuine non-idempotency bug
|
||||||
|
# caught during second-run testing (t_ca1af9fb, 2026-08-31). Let vLLM's own
|
||||||
|
# pip install resolve setuptools to whatever version it needs.
|
||||||
|
|
||||||
|
- name: Install vLLM ({{ vllm_version_spec }})
|
||||||
|
ansible.builtin.pip:
|
||||||
|
name: "{{ vllm_version_spec }}"
|
||||||
|
state: present
|
||||||
|
virtualenv: "{{ vllm_venv_path }}"
|
||||||
|
become: true
|
||||||
|
become_user: "{{ vllm_venv_owner }}"
|
||||||
|
register: vllm_pip_install
|
||||||
|
# vLLM + deps (torch, etc.) is a large download — allow generous time.
|
||||||
|
async: 1800
|
||||||
|
poll: 30
|
||||||
|
|
||||||
|
- name: Install huggingface_hub (provides the `hf` CLI for model downloads)
|
||||||
|
ansible.builtin.pip:
|
||||||
|
name: "huggingface_hub"
|
||||||
|
state: present
|
||||||
|
virtualenv: "{{ vllm_venv_path }}"
|
||||||
|
become: true
|
||||||
|
become_user: "{{ vllm_venv_owner }}"
|
||||||
|
|
||||||
|
- name: Verify vLLM is importable and report version
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "{{ vllm_venv_path }}/bin/python -c 'import vllm; print(vllm.__version__)'"
|
||||||
|
register: vllm_version_check
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: Report vLLM version
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "vLLM version installed: {{ vllm_version_check.stdout }}"
|
||||||
|
|
||||||
|
- name: Verify torch reports CUDA available
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "{{ vllm_venv_path }}/bin/python -c 'import torch; print(torch.cuda.is_available(), torch.version.cuda)'"
|
||||||
|
register: vllm_torch_cuda_check
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: Report torch/CUDA status
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "torch.cuda.is_available(), torch.version.cuda = {{ vllm_torch_cuda_check.stdout }}"
|
||||||
|
|
||||||
|
- name: Warn if CUDA is not available to torch
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: >-
|
||||||
|
WARNING: torch reports CUDA unavailable inside the vLLM venv. Serving will
|
||||||
|
fall back to CPU (unusable for 32B-class models). Check nvidia driver /
|
||||||
|
CUDA wheel compatibility before proceeding to Phase 2.
|
||||||
|
when: "'True' not in vllm_torch_cuda_check.stdout"
|
||||||
@@ -0,0 +1,38 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/tasks/main.yml
|
||||||
|
# ROLE: deploy-vllm — orchestrator. Phased, idempotent, mirrors the pattern
|
||||||
|
# used by roles/llm-inference and roles/llm-inference-multimodel:
|
||||||
|
# Phase 1: dependencies (Python/venv/vLLM/CUDA/nvidia-smi)
|
||||||
|
# Phase 2: model downloads (~/.vllm-cache, checksum-verified)
|
||||||
|
# Phase 3: systemd service(s)
|
||||||
|
# Phase 4: API key management (1Password)
|
||||||
|
# Phase 5: verification (health + smoke test)
|
||||||
|
# Each phase is a separate task file so a partial re-run / targeted --tags
|
||||||
|
# run is possible without re-reading the whole role.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Compute enabled model list (available to every phase/tag combination)
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
vllm_enabled_models: "{{ vllm_models | selectattr('enabled', 'equalto', true) | list }}"
|
||||||
|
tags: [vllm, vllm-dependencies, vllm-models, vllm-api-key, vllm-systemd, vllm-verify]
|
||||||
|
|
||||||
|
- name: Phase 1 — Python & dependencies
|
||||||
|
ansible.builtin.import_tasks: dependencies.yml
|
||||||
|
tags: [vllm, vllm-dependencies]
|
||||||
|
|
||||||
|
- name: Phase 2 — Model downloads
|
||||||
|
ansible.builtin.import_tasks: models.yml
|
||||||
|
tags: [vllm, vllm-models]
|
||||||
|
|
||||||
|
- name: Phase 3 — API key management
|
||||||
|
ansible.builtin.import_tasks: api-key.yml
|
||||||
|
tags: [vllm, vllm-api-key]
|
||||||
|
|
||||||
|
- name: Phase 4 — vLLM systemd service(s)
|
||||||
|
ansible.builtin.import_tasks: systemd.yml
|
||||||
|
tags: [vllm, vllm-systemd]
|
||||||
|
|
||||||
|
- name: Phase 5 — Verification
|
||||||
|
ansible.builtin.import_tasks: verify.yml
|
||||||
|
tags: [vllm, vllm-verify]
|
||||||
|
when: vllm_service_state == 'started'
|
||||||
@@ -0,0 +1,87 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/tasks/models.yml
|
||||||
|
# PHASE 2: Model downloads via huggingface-cli into {{ vllm_hf_hub_cache }}.
|
||||||
|
#
|
||||||
|
# Idempotency: HuggingFace's on-disk cache layout is
|
||||||
|
# {cache}/models--{org}--{repo}/snapshots/{revision}/...
|
||||||
|
# We stat for an existing snapshots dir before downloading — if present with
|
||||||
|
# at least one entry, skip (huggingface-cli download is itself resumable/
|
||||||
|
# idempotent, but this avoids even the "check remote manifest" round trip on
|
||||||
|
# every run and gives a clean "already staged" line in output).
|
||||||
|
#
|
||||||
|
# Pitfall (t_3dddf37d, homelab-llm-inference skill): a config/template landing
|
||||||
|
# is NOT the same as the model being staged. Always verify via `ls`/`du` on
|
||||||
|
# the actual host, never trust a prior task's claim alone.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Ensure model cache directory exists
|
||||||
|
ansible.builtin.file:
|
||||||
|
path: "{{ vllm_hf_hub_cache }}"
|
||||||
|
state: directory
|
||||||
|
owner: "{{ vllm_venv_owner }}"
|
||||||
|
group: "{{ vllm_venv_owner }}"
|
||||||
|
mode: "0755"
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Report models to be staged this run
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "{{ vllm_enabled_models | map(attribute='id') | list }}"
|
||||||
|
|
||||||
|
- name: Check for existing snapshot dir per enabled model
|
||||||
|
ansible.builtin.stat:
|
||||||
|
path: "{{ vllm_hf_hub_cache }}/models--{{ item.hf_repo | regex_replace('/', '--') }}/snapshots"
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_model_snapshot_stat
|
||||||
|
|
||||||
|
- name: Download model repo(s) not yet staged
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: >-
|
||||||
|
{{ vllm_venv_path }}/bin/hf download {{ item.item.hf_repo }}
|
||||||
|
--cache-dir {{ vllm_hf_hub_cache }}
|
||||||
|
become: true
|
||||||
|
become_user: "{{ vllm_venv_owner }}"
|
||||||
|
environment:
|
||||||
|
HF_HUB_ENABLE_HF_TRANSFER: "0"
|
||||||
|
loop: "{{ vllm_model_snapshot_stat.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
|
when: not (item.stat.exists | default(false)) or (item.stat.isdir | default(false) and item.stat.size == 0)
|
||||||
|
register: vllm_model_download
|
||||||
|
# Full-size model pulls (9-18GB for 32B AWQ) can take a long time on
|
||||||
|
# homelab bandwidth — allow up to 1 hour per model.
|
||||||
|
async: 3600
|
||||||
|
poll: 30
|
||||||
|
|
||||||
|
- name: Re-stat snapshot dirs to confirm download landed
|
||||||
|
ansible.builtin.stat:
|
||||||
|
path: "{{ vllm_hf_hub_cache }}/models--{{ item.hf_repo | regex_replace('/', '--') }}/snapshots"
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_model_snapshot_verify
|
||||||
|
|
||||||
|
- name: Fail if any enabled model failed to stage
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "Model {{ item.item.id }} ({{ item.item.hf_repo }}) is not present at {{ vllm_hf_hub_cache }} after download step."
|
||||||
|
loop: "{{ vllm_model_snapshot_verify.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
|
when: not (item.stat.exists | default(false))
|
||||||
|
|
||||||
|
- name: Compute on-disk size of each staged model (sanity check, not a strict checksum)
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "du -sh {{ vllm_hf_hub_cache }}/models--{{ item.hf_repo | regex_replace('/', '--') }}"
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_model_size
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: Report staged model sizes
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "{{ item.stdout }}"
|
||||||
|
loop: "{{ vllm_model_size.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
@@ -0,0 +1,56 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/tasks/systemd.yml
|
||||||
|
# PHASE 4: vLLM systemd service(s).
|
||||||
|
#
|
||||||
|
# vLLM 0.5.x serves ONE model per process. The primary model (role: primary,
|
||||||
|
# e.g. Qwen2.5-32B-Instruct-AWQ) gets the canonical unit name vllm.service
|
||||||
|
# (matches the spec's /etc/systemd/system/vllm.service). Any additional
|
||||||
|
# enabled models (aux/embedding, added in later phases per the "Phased
|
||||||
|
# Strategy") each get their own instance unit vllm-<id>.service on a distinct
|
||||||
|
# port, generated from the same template.
|
||||||
|
#
|
||||||
|
# Idempotent: ansible.builtin.template only reports changed when content
|
||||||
|
# actually differs; the "restart vllm services" handler only fires on that
|
||||||
|
# change (or on api-key.yml rewriting the shared env file).
|
||||||
|
#
|
||||||
|
# vllm_service_state defaults to "stopped" — this role stages everything
|
||||||
|
# (venv, model, unit file, key) but does NOT flip production traffic without
|
||||||
|
# an explicit --extra-vars vllm_service_state=started, matching the deploy-
|
||||||
|
# then-validate-then-cutover sequencing approved for astro-orbiter.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Render systemd unit for each enabled model
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: vllm.service.j2
|
||||||
|
dest: "/etc/systemd/system/{{ 'vllm.service' if item.role == 'primary' else 'vllm-' + item.id + '.service' }}"
|
||||||
|
owner: root
|
||||||
|
group: root
|
||||||
|
mode: "0644"
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
become: true
|
||||||
|
notify: reload systemd
|
||||||
|
|
||||||
|
- name: Render workspace helper script (manual debugging / smoke-testing)
|
||||||
|
ansible.builtin.template:
|
||||||
|
src: vllm-workspace.sh.j2
|
||||||
|
dest: "/home/{{ vllm_venv_owner }}/vllm-workspace.sh"
|
||||||
|
owner: "{{ vllm_venv_owner }}"
|
||||||
|
group: "{{ vllm_venv_owner }}"
|
||||||
|
mode: "0750"
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Flush handlers so unit files are known to systemd before enabling
|
||||||
|
ansible.builtin.meta: flush_handlers
|
||||||
|
|
||||||
|
- name: Enable/disable + start/stop each vLLM systemd unit
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: "{{ 'vllm.service' if item.role == 'primary' else 'vllm-' + item.id + '.service' }}"
|
||||||
|
enabled: "{{ vllm_service_enabled }}"
|
||||||
|
state: "{{ vllm_service_state }}"
|
||||||
|
daemon_reload: true
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
become: true
|
||||||
@@ -0,0 +1,163 @@
|
|||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: roles/deploy-vllm/tasks/verify.yml
|
||||||
|
# PHASE 5: Verification.
|
||||||
|
#
|
||||||
|
# Only runs when vllm_service_state == 'started' (main.yml gate) — staging a
|
||||||
|
# stopped service is a valid, intentional end state during the deploy-first-
|
||||||
|
# validate-before-cutover sequencing, and there is nothing to verify yet.
|
||||||
|
#
|
||||||
|
# Pitfall (homelab-llm-inference skill): vLLM torch.compile takes 4+ minutes
|
||||||
|
# AFTER weights load before /health returns 200. retries=30, delay=10 (5 min
|
||||||
|
# ceiling) — do not shrink this or health checks will false-negative on a
|
||||||
|
# perfectly healthy but still-warming-up service.
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
- name: Wait for each enabled model's systemd unit to be active
|
||||||
|
ansible.builtin.systemd:
|
||||||
|
name: "{{ 'vllm.service' if item.role == 'primary' else 'vllm-' + item.id + '.service' }}"
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_unit_status
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Report systemd unit status
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "{{ item.item.id }}: {{ item.status.ActiveState }} ({{ item.status.SubState }})"
|
||||||
|
loop: "{{ vllm_unit_status.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
|
|
||||||
|
- name: Fail if any unit is not active
|
||||||
|
ansible.builtin.fail:
|
||||||
|
msg: "{{ item.item.id }} systemd unit is {{ item.status.ActiveState }}, expected active."
|
||||||
|
loop: "{{ vllm_unit_status.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
|
when: item.status.ActiveState != 'active'
|
||||||
|
|
||||||
|
- name: Poll /health until 200 (torch.compile warmup can take 4-5 minutes)
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://127.0.0.1:{{ item.port }}/health"
|
||||||
|
status_code: 200
|
||||||
|
timeout: 15
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_health_check
|
||||||
|
until: vllm_health_check is succeeded
|
||||||
|
retries: "{{ vllm_health_check_retries }}"
|
||||||
|
delay: "{{ vllm_health_check_delay }}"
|
||||||
|
|
||||||
|
- name: Query /v1/models on each enabled instance
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://127.0.0.1:{{ item.port }}/v1/models"
|
||||||
|
headers:
|
||||||
|
Authorization: "Bearer {{ vllm_api_key_lookup.stdout }}"
|
||||||
|
return_content: true
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_models_response
|
||||||
|
no_log: true
|
||||||
|
|
||||||
|
- name: Assert /v1/models returns the expected served model name
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- item.item.id in (item.content)
|
||||||
|
fail_msg: "/v1/models on port {{ item.item.port }} did not list expected model id {{ item.item.id }}"
|
||||||
|
success_msg: "/v1/models confirmed {{ item.item.id }} is served on port {{ item.item.port }}"
|
||||||
|
loop: "{{ vllm_models_response.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
|
|
||||||
|
- name: Split enabled models into completion-serving vs embedding for the right smoke test
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
vllm_completion_models: "{{ vllm_enabled_models | rejectattr('role', 'equalto', 'embedding') | list }}"
|
||||||
|
vllm_embedding_models: "{{ vllm_enabled_models | selectattr('role', 'equalto', 'embedding') | list }}"
|
||||||
|
|
||||||
|
- name: Run a live completion smoke test against each completion-serving instance
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://127.0.0.1:{{ item.port }}/v1/completions"
|
||||||
|
method: POST
|
||||||
|
headers:
|
||||||
|
Authorization: "Bearer {{ vllm_api_key_lookup.stdout }}"
|
||||||
|
Content-Type: "application/json"
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "{{ item.id }}"
|
||||||
|
prompt: "The capital of France is"
|
||||||
|
max_tokens: 8
|
||||||
|
temperature: 0
|
||||||
|
timeout: 60
|
||||||
|
status_code: 200
|
||||||
|
loop: "{{ vllm_completion_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_completion_test
|
||||||
|
no_log: true
|
||||||
|
|
||||||
|
- name: Report completion smoke test result
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "{{ item.item.id }}: HTTP {{ item.status }} — completion smoke test passed"
|
||||||
|
loop: "{{ vllm_completion_test.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
|
|
||||||
|
# Embedding-mode vLLM instances (--runner pooling --convert embed) do NOT
|
||||||
|
# serve /v1/completions — only /v1/embeddings (and /pooling). A completions
|
||||||
|
# smoke test against one 400s immediately. Verify with a real vector request
|
||||||
|
# instead, and assert the response actually contains a non-empty float vector
|
||||||
|
# (not just HTTP 200 — an empty/malformed embedding would still 200).
|
||||||
|
- name: Run a live embeddings smoke test against each embedding-mode instance
|
||||||
|
ansible.builtin.uri:
|
||||||
|
url: "http://127.0.0.1:{{ item.port }}/v1/embeddings"
|
||||||
|
method: POST
|
||||||
|
headers:
|
||||||
|
Authorization: "Bearer {{ vllm_api_key_lookup.stdout }}"
|
||||||
|
Content-Type: "application/json"
|
||||||
|
body_format: json
|
||||||
|
body:
|
||||||
|
model: "{{ item.id }}"
|
||||||
|
input: "The capital of France is Paris."
|
||||||
|
timeout: 60
|
||||||
|
status_code: 200
|
||||||
|
return_content: true
|
||||||
|
loop: "{{ vllm_embedding_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_embedding_test
|
||||||
|
no_log: true
|
||||||
|
|
||||||
|
- name: Assert embeddings smoke test returned a non-empty float vector
|
||||||
|
ansible.builtin.assert:
|
||||||
|
that:
|
||||||
|
- (item.json.data[0].embedding | length) > 0
|
||||||
|
fail_msg: "/v1/embeddings on port {{ item.item.port }} did not return a non-empty embedding vector"
|
||||||
|
success_msg: "/v1/embeddings confirmed {{ item.item.id }} returns a {{ item.json.data[0].embedding | length }}-dim vector"
|
||||||
|
loop: "{{ vllm_embedding_test.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
|
|
||||||
|
- name: Check journalctl for each enabled unit is free of ERROR/Traceback since last start
|
||||||
|
ansible.builtin.shell: |
|
||||||
|
set -o pipefail
|
||||||
|
journalctl -u {{ 'vllm.service' if item.role == 'primary' else 'vllm-' + item.id + '.service' }} --since "10 min ago" | grep -iE "error|traceback" | grep -v "no entries" || true
|
||||||
|
args:
|
||||||
|
executable: /bin/bash
|
||||||
|
loop: "{{ vllm_enabled_models }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.id }}"
|
||||||
|
register: vllm_journal_errors
|
||||||
|
changed_when: false
|
||||||
|
become: true
|
||||||
|
|
||||||
|
- name: Report journalctl scan result
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: >-
|
||||||
|
{{ item.item.id ~ ': journalctl clean — no error/traceback lines in the last 10 minutes'
|
||||||
|
if item.stdout | trim | length == 0
|
||||||
|
else item.item.id ~ ' WARNING — journalctl lines matched error/traceback: ' ~ item.stdout }}
|
||||||
|
loop: "{{ vllm_journal_errors.results }}"
|
||||||
|
loop_control:
|
||||||
|
label: "{{ item.item.id }}"
|
||||||
@@ -0,0 +1,54 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
# FILE: vllm-workspace.sh — deployed by roles/deploy-vllm to
|
||||||
|
# /home/{{ vllm_venv_owner }}/vllm-workspace.sh
|
||||||
|
#
|
||||||
|
# Convenience wrapper for manual debugging / smoke-testing the vLLM venv
|
||||||
|
# without having to remember the venv path or model roster each time.
|
||||||
|
# Regenerated on every Ansible run — do not hand-edit, edit the template
|
||||||
|
# instead (roles/deploy-vllm/templates/vllm-workspace.sh.j2).
|
||||||
|
# ------------------------------------------------------------------------------
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
VENV="{{ vllm_venv_path }}"
|
||||||
|
CACHE="{{ vllm_hf_hub_cache }}"
|
||||||
|
API_KEY_FILE="{{ vllm_api_key_env_file }}"
|
||||||
|
|
||||||
|
usage() {
|
||||||
|
cat <<EOF
|
||||||
|
Usage: $0 <command>
|
||||||
|
|
||||||
|
Commands:
|
||||||
|
activate Print the command to source the vLLM venv
|
||||||
|
version Print installed vLLM + torch/CUDA versions
|
||||||
|
models List staged model snapshots in the HF cache
|
||||||
|
curl-models curl /v1/models on each enabled instance (requires sudo to read API key)
|
||||||
|
logs <unit> Tail journalctl for a vllm systemd unit (e.g. vllm.service)
|
||||||
|
EOF
|
||||||
|
}
|
||||||
|
|
||||||
|
case "${1:-}" in
|
||||||
|
activate)
|
||||||
|
echo "source $VENV/bin/activate"
|
||||||
|
;;
|
||||||
|
version)
|
||||||
|
"$VENV/bin/python" -c 'import vllm, torch; print("vllm", vllm.__version__); print("torch", torch.__version__, "cuda", torch.version.cuda, "available", torch.cuda.is_available())'
|
||||||
|
;;
|
||||||
|
models)
|
||||||
|
find "$CACHE" -maxdepth 1 -type d -name 'models--*' -printf '%f\n' 2>/dev/null || echo "(no models staged yet)"
|
||||||
|
;;
|
||||||
|
curl-models)
|
||||||
|
{% for item in vllm_enabled_models | default([]) %}
|
||||||
|
echo "--- {{ item.id }} (:{{ item.port }}) ---"
|
||||||
|
curl -s -H "Authorization: Bearer $(sudo grep -oP '(?<=VLLM_API_KEY=).*' "$API_KEY_FILE")" \
|
||||||
|
http://127.0.0.1:{{ item.port }}/v1/models | python3 -m json.tool || true
|
||||||
|
{% endfor %}
|
||||||
|
;;
|
||||||
|
logs)
|
||||||
|
sudo journalctl -u "${2:-vllm.service}" -f
|
||||||
|
;;
|
||||||
|
*)
|
||||||
|
usage
|
||||||
|
exit 1
|
||||||
|
;;
|
||||||
|
esac
|
||||||
@@ -0,0 +1,85 @@
|
|||||||
|
[Unit]
|
||||||
|
Description=vLLM OpenAI-compatible inference server — {{ item.id }} ({{ item.hf_repo }})
|
||||||
|
After=network-online.target nvidia-persistenced.service
|
||||||
|
Wants=network-online.target nvidia-persistenced.service
|
||||||
|
|
||||||
|
[Service]
|
||||||
|
Type=simple
|
||||||
|
User={{ vllm_venv_owner }}
|
||||||
|
Group={{ vllm_venv_owner }}
|
||||||
|
EnvironmentFile={{ vllm_api_key_env_file }}
|
||||||
|
Environment="HOME=/home/{{ vllm_venv_owner }}"
|
||||||
|
Environment="HF_HUB_CACHE={{ vllm_hf_hub_cache }}"
|
||||||
|
Environment="HF_HOME={{ vllm_cache_dir }}"
|
||||||
|
# vLLM's torch.compile path shells out to `ninja` by bare name (not via
|
||||||
|
# venv-relative path) — without the venv's bin/ on PATH, systemd's minimal
|
||||||
|
# default PATH causes FileNotFoundError: 'ninja' deep in compile, even
|
||||||
|
# though `pip install vllm` installs the ninja package (and its console
|
||||||
|
# script) INTO the venv. Caught during Phase 5 validation (t_ca1af9fb,
|
||||||
|
# 2026-08-31): interactive SSH sessions have a different PATH than systemd
|
||||||
|
# services, so this only reproduces under systemd, not manual testing.
|
||||||
|
Environment="PATH={{ vllm_venv_path }}/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||||||
|
# FlashInfer's bundled sampling.cu JIT-compiles against a cub template API
|
||||||
|
# (BlockAdjacentDifference::FlagHeads) that this flashinfer/CUDA toolkit
|
||||||
|
# combination does not provide on RTX 3090 (SM86) — 100 compile errors,
|
||||||
|
# confirmed upstream-known (vLLM GH #23023, #44305: FlashInfer sampler JIT
|
||||||
|
# breaks on various SM targets across flashinfer/vLLM version combos).
|
||||||
|
# Falls back to vLLM's native PyTorch sampler, which is fully supported and
|
||||||
|
# only marginally slower for single-request/low-concurrency serving. Caught
|
||||||
|
# during Phase 5 validation (t_ca1af9fb, 2026-08-31).
|
||||||
|
Environment="VLLM_USE_FLASHINFER_SAMPLER=0"
|
||||||
|
|
||||||
|
ExecStart={{ vllm_venv_path }}/bin/python -m vllm.entrypoints.openai.api_server \
|
||||||
|
--model {{ item.hf_repo }} \
|
||||||
|
--served-model-name {{ item.id }} \
|
||||||
|
--host {{ vllm_serve_host }} \
|
||||||
|
--port {{ item.port }} \
|
||||||
|
{% if item.role == 'embedding' %}
|
||||||
|
--runner pooling \
|
||||||
|
--convert embed \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.trust_remote_code is defined and item.trust_remote_code %}
|
||||||
|
--trust-remote-code \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.enforce_eager is defined and item.enforce_eager %}
|
||||||
|
--enforce-eager \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.enable_auto_tool_choice is defined and item.enable_auto_tool_choice %}
|
||||||
|
--enable-auto-tool-choice \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.tool_call_parser is defined %}
|
||||||
|
--tool-call-parser {{ item.tool_call_parser }} \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.reasoning_parser is defined %}
|
||||||
|
--reasoning-parser {{ item.reasoning_parser }} \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.quantization is defined and item.quantization != 'none' %}
|
||||||
|
--quantization {{ item.quantization }} \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.kv_cache_dtype is defined %}
|
||||||
|
--kv-cache-dtype {{ item.kv_cache_dtype }} \
|
||||||
|
{% endif %}
|
||||||
|
{% if item.kv_cache_memory_bytes is defined %}
|
||||||
|
--kv-cache-memory-bytes {{ item.kv_cache_memory_bytes }} \
|
||||||
|
{% endif %}
|
||||||
|
--gpu-memory-utilization {{ item.gpu_memory_utilization }} \
|
||||||
|
--max-model-len {{ item.max_model_len }} \
|
||||||
|
--dtype {{ vllm_dtype }} \
|
||||||
|
--api-key ${VLLM_API_KEY} \
|
||||||
|
{% if item.role != 'embedding' %}
|
||||||
|
--enable-prefix-caching
|
||||||
|
{% else %}
|
||||||
|
--no-enable-prefix-caching
|
||||||
|
{% endif %}
|
||||||
|
|
||||||
|
Restart={{ vllm_restart_policy }}
|
||||||
|
RestartSec=10
|
||||||
|
# vLLM torch.compile can take 4+ minutes before /health responds even after
|
||||||
|
# weights are loaded (homelab-llm-inference skill pitfall) — give it room.
|
||||||
|
TimeoutStartSec=600
|
||||||
|
StandardOutput=journal
|
||||||
|
StandardError=journal
|
||||||
|
SyslogIdentifier=vllm-{{ item.id }}
|
||||||
|
|
||||||
|
[Install]
|
||||||
|
WantedBy=multi-user.target
|
||||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
@@ -0,0 +1,95 @@
|
|||||||
|
# expand-root-lv role
|
||||||
|
|
||||||
|
Idempotent role that grows the root partition (via `growpart`), extends the
|
||||||
|
root LVM logical volume to fill its volume group, and grows the underlying
|
||||||
|
filesystem (ext4 or xfs).
|
||||||
|
|
||||||
|
## Where this runs in the lifecycle
|
||||||
|
|
||||||
|
Part of the **day0** host-provisioning lifecycle. The canonical entry
|
||||||
|
points are:
|
||||||
|
|
||||||
|
```
|
||||||
|
playbooks/day0_expand_root_lv.yml # standalone
|
||||||
|
playbooks/day0_provision.yml # umbrella (baseline + expand_root_lv)
|
||||||
|
```
|
||||||
|
|
||||||
|
Day1 application-deploy playbooks should NOT include this role —
|
||||||
|
day0 is assumed complete before day1 begins.
|
||||||
|
|
||||||
|
## Why this role exists
|
||||||
|
|
||||||
|
The Ubuntu Server autoinstall template (used by the mk-labs `wed`-baked
|
||||||
|
VM templates) provisions the root LV at roughly half the available disk
|
||||||
|
size — a longstanding installer default that surprises every operator
|
||||||
|
who hasn't been bitten by it before. ~90% of mk-labs VMs need this
|
||||||
|
fix-up before they're fully useful.
|
||||||
|
|
||||||
|
After a Proxmox disk grow (increasing the VM disk size), the partition
|
||||||
|
table, physical volume, logical volume, and filesystem all need to be
|
||||||
|
extended in sequence. This role automates the full chain.
|
||||||
|
|
||||||
|
## Workflow
|
||||||
|
|
||||||
|
1. **growpart** — resizes the underlying partition to claim the newly
|
||||||
|
provisioned disk space. Idempotent: no-op when the partition already
|
||||||
|
fills the disk.
|
||||||
|
2. **pvresize** — tells the kernel/LVM about the new partition size so
|
||||||
|
the VG sees the additional free PEs.
|
||||||
|
3. **lvextend** — extends the LV to claim all free PE in the VG
|
||||||
|
(`+100%FREE`). No-op when there's nothing to grow.
|
||||||
|
4. **fs grow** — `resize2fs` (ext4) or `xfs_growfs` (xfs), dispatched by
|
||||||
|
detected filesystem type.
|
||||||
|
|
||||||
|
## Idempotency
|
||||||
|
|
||||||
|
- If `vg_free_count == 0`, the `lvextend` step is skipped and the
|
||||||
|
filesystem-grow step is also skipped (nothing to resize against).
|
||||||
|
- If the target volume group doesn't exist on the host (e.g. a non-LVM
|
||||||
|
layout), the role exits cleanly via `meta: end_play`.
|
||||||
|
- Safe to leave in a recurring playbook so future disk expansions
|
||||||
|
(Proxmox-side disk grow → reboot → run role) are picked up
|
||||||
|
automatically.
|
||||||
|
|
||||||
|
## Opt-out for multi-LV hosts
|
||||||
|
|
||||||
|
If a host will have a **second logical volume in the same VG** (e.g. a
|
||||||
|
dedicated `/var/lib/postgresql` LV for a database server), this role's
|
||||||
|
"grow root to fill VG" behavior is wrong — it will consume the free PE
|
||||||
|
that was being reserved for the second LV.
|
||||||
|
|
||||||
|
Set in `host_vars/<host>.yml`:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
expand_root_lv_skip: true
|
||||||
|
```
|
||||||
|
|
||||||
|
The day0 playbook checks this flag and skips the role cleanly.
|
||||||
|
|
||||||
|
To skip only the partition growstep while keeping LV/FS expansion
|
||||||
|
(e.g. when the partition already covers the whole disk but the LV was
|
||||||
|
provisioned small by the template), set:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
expand_root_lv_pv_partition: undefined
|
||||||
|
```
|
||||||
|
|
||||||
|
## Defaults
|
||||||
|
|
||||||
|
| Variable | Default | Purpose |
|
||||||
|
|-------------------------------|---------------|-----------------------------------------------------|
|
||||||
|
| `expand_root_lv_vg_name` | `ubuntu-vg` | LVM volume group name (Ubuntu installer default). |
|
||||||
|
| `expand_root_lv_lv_name` | `ubuntu-lv` | LVM logical volume name (Ubuntu installer default). |
|
||||||
|
| `expand_root_lv_pv_partition` | `/dev/sda3` | Partition backing the PV; grown via growpart. |
|
||||||
|
| `expand_root_lv_mountpoint` | `/` | Mountpoint of the filesystem to grow. |
|
||||||
|
|
||||||
|
Override the VG/LV/PV names in `host_vars/<host>.yml` for hosts that use a
|
||||||
|
different layout.
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
- The `growpart` step requires the `cloud-guest-utils` package. The role
|
||||||
|
installs it automatically on Debian/Ubuntu hosts when
|
||||||
|
`expand_root_lv_pv_partition` is defined.
|
||||||
|
- Only supports ext4 and xfs filesystems. Other filesystem types (btrfs,
|
||||||
|
etc.) are left as a future enhancement.
|
||||||
@@ -0,0 +1,32 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# expand-root-lv role defaults
|
||||||
|
# ============================================================================
|
||||||
|
# Extends the root LVM logical volume to fill its volume group, then grows
|
||||||
|
# the underlying filesystem to match. Idempotent: when there's no free PE
|
||||||
|
# in the VG (i.e. the LV already fills the VG), the lvextend step is a
|
||||||
|
# no-op and resize2fs/xfs_growfs simply confirms the filesystem is at
|
||||||
|
# capacity.
|
||||||
|
#
|
||||||
|
# Designed for Ubuntu cloud-image-style installations where the autoinstall
|
||||||
|
# template provisions an LV at half the disk size (the Ubuntu Server
|
||||||
|
# installer's longstanding default). Run once after VM provisioning to
|
||||||
|
# reclaim the unallocated PE; safe to leave in a day1 playbook so future
|
||||||
|
# disk expansions are picked up automatically.
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
# The LV and VG names follow the Ubuntu Server installer's convention.
|
||||||
|
# Override per-host if your template differs.
|
||||||
|
expand_root_lv_vg_name: ubuntu-vg
|
||||||
|
expand_root_lv_lv_name: ubuntu-lv
|
||||||
|
|
||||||
|
# The partition that backs the physical volume. After a Proxmox disk grow,
|
||||||
|
# growpart must resize this partition before pvresize/lvextend can claim
|
||||||
|
# the new space. This is the full device path (e.g. /dev/sda3).
|
||||||
|
# If undefined, the growpart/pvresize steps are skipped.
|
||||||
|
expand_root_lv_pv_partition: /dev/sda3
|
||||||
|
|
||||||
|
# Mount point we expect to be backed by the target LV. Used purely for
|
||||||
|
# the resize2fs / xfs_growfs decision — the role inspects this path's
|
||||||
|
# filesystem type and dispatches to the correct grow command.
|
||||||
|
expand_root_lv_mountpoint: /
|
||||||
@@ -0,0 +1,23 @@
|
|||||||
|
---
|
||||||
|
galaxy_info:
|
||||||
|
role_name: expand_root_lv
|
||||||
|
author: JARVIS
|
||||||
|
description: >-
|
||||||
|
Idempotent role that extends the root LVM logical volume to fill its
|
||||||
|
volume group and grows the underlying filesystem (ext4 or xfs). Fixes
|
||||||
|
the half-disk LV that the Ubuntu Server autoinstall template ships
|
||||||
|
with by default.
|
||||||
|
license: MIT
|
||||||
|
min_ansible_version: "2.14"
|
||||||
|
platforms:
|
||||||
|
- name: Ubuntu
|
||||||
|
versions:
|
||||||
|
- noble
|
||||||
|
- jammy
|
||||||
|
galaxy_tags:
|
||||||
|
- lvm
|
||||||
|
- cloud-init
|
||||||
|
- homelab
|
||||||
|
- storage
|
||||||
|
|
||||||
|
dependencies: []
|
||||||
@@ -0,0 +1,147 @@
|
|||||||
|
---
|
||||||
|
# ============================================================================
|
||||||
|
# expand-root-lv / main
|
||||||
|
# ----------------------------------------------------------------------------
|
||||||
|
# 0. Ensure growpart is available (cloud-guest-utils provides the growpart binary)
|
||||||
|
# 1. Grow the partition (growpart) if a PV partition device is defined
|
||||||
|
# 2. Resize the physical volume (pvresize) to pick up the new partition size
|
||||||
|
# 3. Confirm the target VG exists (skip role cleanly on non-LVM hosts).
|
||||||
|
# 4. Read free physical-extent count for the VG.
|
||||||
|
# 5. Extend the LV to +100%FREE only when free_pe > 0.
|
||||||
|
# 6. Grow the filesystem on the mountpoint (ext4 -> resize2fs, xfs -> xfs_growfs).
|
||||||
|
# Each step is idempotent and skips when there's nothing to do.
|
||||||
|
# ============================================================================
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 0: Ensure growpart is available
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
- name: Ensure cloud-guest-utils (growpart) is installed
|
||||||
|
ansible.builtin.package:
|
||||||
|
name: cloud-guest-utils
|
||||||
|
state: present
|
||||||
|
when: expand_root_lv_pv_partition is defined
|
||||||
|
tags: [growpart, always]
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 1: Grow the partition that backs the PV
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# growpart expects: growpart <device> <partition_number>
|
||||||
|
# e.g. growpart /dev/sda 3 — NOT growpart /dev/sda3
|
||||||
|
# We split expand_root_lv_pv_partition (e.g. /dev/sda3) into device and part_no.
|
||||||
|
|
||||||
|
- name: Derive device and partition number from PV partition path
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
expand_root_lv_pv_device: "{{ expand_root_lv_pv_partition | regex_replace('p?(\\d+)$', '') }}"
|
||||||
|
expand_root_lv_pv_part_no: "{{ expand_root_lv_pv_partition | regex_replace('.*p?(\\d+)$', '\\1') }}"
|
||||||
|
when: expand_root_lv_pv_partition is defined
|
||||||
|
tags: [growpart, always]
|
||||||
|
|
||||||
|
- name: Grow partition to fill disk (growpart)
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "growpart {{ expand_root_lv_pv_device }} {{ expand_root_lv_pv_part_no }}"
|
||||||
|
register: growpart_result
|
||||||
|
when: expand_root_lv_pv_partition is defined
|
||||||
|
changed_when: growpart_result.rc == 0 and "NO CHANGE" not in growpart_result.stdout
|
||||||
|
tags: [growpart, always]
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 2: Resize the physical volume to claim the new partition space
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
- name: Resize physical volume (pvresize)
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "pvresize {{ expand_root_lv_pv_partition }}"
|
||||||
|
register: pvresize_result
|
||||||
|
when: expand_root_lv_pv_partition is defined
|
||||||
|
changed_when: pvresize_result.rc == 0
|
||||||
|
tags: [pvresize, always]
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 3: Confirm the target VG exists (skip role cleanly on non-LVM hosts).
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
- name: Gather LVM facts
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "vgs --noheadings --nosuffix --units b -o vg_name,vg_free_count {{ expand_root_lv_vg_name }}"
|
||||||
|
register: vg_info
|
||||||
|
changed_when: false
|
||||||
|
failed_when: false
|
||||||
|
tags: [lvm, always]
|
||||||
|
|
||||||
|
- name: Skip role when target VG is absent
|
||||||
|
ansible.builtin.meta: end_play
|
||||||
|
when: vg_info.rc != 0
|
||||||
|
tags: [lvm, always]
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 4: Parse free PE count for the VG
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
- name: Parse free PE count
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
expand_root_lv_free_pe: "{{ (vg_info.stdout.split() | last | int) if vg_info.stdout | length > 0 else 0 }}"
|
||||||
|
tags: [lvm, always]
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 5: Extend the LV to +100%FREE only when free_pe > 0
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
- name: Extend LV to fill VG (only if free PE > 0)
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "lvextend -l +100%FREE /dev/{{ expand_root_lv_vg_name }}/{{ expand_root_lv_lv_name }}"
|
||||||
|
register: lvextend_result
|
||||||
|
when: expand_root_lv_free_pe | int > 0
|
||||||
|
changed_when: lvextend_result.rc == 0
|
||||||
|
tags: [lvm, always]
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 6: Detect filesystem type at mountpoint and grow
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
- name: Detect filesystem type at mountpoint
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "findmnt {{ expand_root_lv_mountpoint }} -no FSTYPE"
|
||||||
|
register: fstype_result
|
||||||
|
changed_when: false
|
||||||
|
tags: [filesystem, always]
|
||||||
|
|
||||||
|
- name: Set filesystem type fact
|
||||||
|
ansible.builtin.set_fact:
|
||||||
|
expand_root_lv_fstype: "{{ fstype_result.stdout | trim }}"
|
||||||
|
tags: [filesystem, always]
|
||||||
|
|
||||||
|
- name: Grow ext4 filesystem
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "resize2fs /dev/{{ expand_root_lv_vg_name }}/{{ expand_root_lv_lv_name }}"
|
||||||
|
register: resize_result
|
||||||
|
when:
|
||||||
|
- expand_root_lv_fstype == "ext4"
|
||||||
|
- (growpart_result is defined and growpart_result.changed) or
|
||||||
|
(pvresize_result is defined and pvresize_result.changed) or
|
||||||
|
(lvextend_result is defined and lvextend_result.changed) or
|
||||||
|
(growpart_result is not defined)
|
||||||
|
changed_when: resize_result.rc == 0
|
||||||
|
tags: [filesystem, always]
|
||||||
|
|
||||||
|
- name: Grow xfs filesystem
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "xfs_growfs {{ expand_root_lv_mountpoint }}"
|
||||||
|
register: xfs_result
|
||||||
|
when:
|
||||||
|
- expand_root_lv_fstype == "xfs"
|
||||||
|
- (growpart_result is defined and growpart_result.changed) or
|
||||||
|
(pvresize_result is defined and pvresize_result.changed) or
|
||||||
|
(lvextend_result is defined and lvextend_result.changed) or
|
||||||
|
(growpart_result is not defined)
|
||||||
|
changed_when: xfs_result.rc == 0
|
||||||
|
tags: [filesystem, always]
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Step 7: Report current root size
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
- name: Report current root size
|
||||||
|
ansible.builtin.command:
|
||||||
|
cmd: "df -h {{ expand_root_lv_mountpoint }}"
|
||||||
|
register: df_result
|
||||||
|
changed_when: false
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
- name: Show post-resize disk usage
|
||||||
|
ansible.builtin.debug:
|
||||||
|
msg: "{{ df_result.stdout_lines }}"
|
||||||
|
tags: [always]
|
||||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
Loaded 100 of 570 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user