homelab/ansible/host_vars/astro-orbiter/vars.yml

---
# ------------------------------------------------------------------------------
# FILE: ansible/host_vars/astro_orbiter/vars.yml
# HOST: astro-orbiter (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 Superseded the prior AMD RX 5700 / Ollama config below;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_e6facb19, 2026-08-31) --------
# 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.
# This is therefore a full copy of roles/deploy-vllm/defaults/main.yml's
# vllm_models with ONE change: nomic-embed-text-v1.5.enabled flipped to true,
# now that vllm.service.j2 has an embedding-mode branch (--runner pooling
# --convert embed --trust-remote-code) tested end-to-end in a shadow window.
# Primary (Qwen2.5-32B-Instruct-AWQ) and aux (Qwen3-8B-AWQ) entries are
# unchanged from role defaults — reproduced here only because the whole list
# must be redefined together. Keep this in sync with defaults/main.yml if the
# role's model roster changes.
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: 8192
    # 0.95 (role default) OOM'd during CUDA graph capture once nomic-embed
    # (role: embedding, ~814MiB actual, not the nominal 300MB) is co-resident
    # on the same 24GB card (t_e6facb19, 2026-08-31): KV cache allocation
    # succeeded (14,720 tokens) but graph capture needed ~20MiB more than the
    # 0.95 budget left after nomic's share. Two independent, permanent
    # co-residents (unlike t_ca1af9fb's shadow-window test, which had the
    # whole 24GB free) need either a lower utilization ceiling or no graph
    # capture. enforce_eager avoids the whole cudagraph capture memory spike
    # entirely — small throughput cost, no OOM risk, safer for a fixed
    # multi-process VRAM budget than tuning utilization percentages by hand.
    # Even WITH enforce_eager, 0.95 left only ~847MiB genuinely free out of
    # 24576MiB total (23,729MiB used) and both services crash-looped 6-7x
    # during warmup/KV-cache sizing before stabilizing — too fragile for a
    # permanent two-process co-residency. Lowered to 0.90 for real headroom
    # (~1.6GiB free), confirmed clean single-attempt start with no retries.
    gpu_memory_utilization: 0.90
    enforce_eager: true
    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
    trust_remote_code: true
    enabled: true

# --- deploy-vllm role: boot persistence NOT enabled (t_e6facb19, 2026-08-31) ---
# ATTEMPTED enabling vllm_service_enabled/state=started here, then reverted
# after a production-breaking discovery: with vLLM's two processes
# (Qwen2.5-32B + nomic-embed, ~22.8GB combined) resident, 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
# "upstream command exited prematurely" (llama-server's own OOM at spawn
# time, silently swallowed by llama-swap's generic error). Confirmed by
# direct A/B: same request 500s with vLLM running, 200s within seconds of
# `systemctl stop vllm.service vllm-nomic-embed-text-v1.5.service`. This
# breaks all 21 Hermes agent profiles' aux-model tasks (skills_hub, approval,
# mcp, title_generation, profile_describer, compression) plus OpenViking's
# VLM -- a severe regression, worse than the status quo. Left
# vllm_service_enabled/state at role defaults (false/stopped) -- vLLM stays
# staged and manually startable for a brief shadow window (same pattern as
# t_ca1af9fb's original validation), but is NOT safe to leave resident
# alongside llama-swap on this 24GB card. See README's "Known Gaps" section:
# full teardown of llama-swap (t_6dff1ecc) is the ONLY path to giving vLLM
# permanent residency without starving the other models -- this is not
# solvable by tuning gpu_memory_utilization further, the two stacks
# together need more VRAM than this card has once both hold real models
# resident.