rblundon/homelab
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

monitoring: llama-swap GPU/LLM stack (v250) — PrometheusRule, Grafana dashboard, scrape config, VRAM exporter

Browse Source
This commit is contained in:
Hermes Agent service account
2026-08-18 22:22:53 -05:00
parent 03b3ce9dee
commit 7867be688a
17 changed files with 2951 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

556
cluster/applications/monitoring/llama-swap-dashboard.yaml Normal file
View File

@@ -0,0 +1,556 @@
---
# ------------------------------------------------------------------------------
# FILE: cluster/applications/monitoring/llama-swap-dashboard.yaml
# DESCRIPTION: Custom Grafana dashboard for llama-swap GPU/LLM monitoring.
# Picked up automatically by the Grafana sidecar via label:
# grafana_dashboard: "1"
# Based on the Ciro Luciotta homelab LLM monitoring pattern.
#
# USAGE: This ConfigMap is reconciled by ArgoCD. The dashboard JSON is
# embedded inline (data key ends in .json).
# ------------------------------------------------------------------------------
apiVersion: v1
kind: ConfigMap
metadata:
name: dashboard-llama-swap
namespace: monitoring
labels:
grafana_dashboard: "1"
app.kubernetes.io/part-of: monitoring
data:
llama-swap.json: |
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"id": null,
"links": [],
"panels": [
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "MiB",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 24576,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 23000
},
{
"color": "red",
"value": 24000
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"legend": {
"calcs": [
"last",
"max"
],
"displayMode": "table",
"placement": "right"
},
"tooltip": {
"mode": "single"
}
},
"pluginVersion": "8.0.0",
"targets": [
{
"expr": "llamacpp_vram_used_mib{job=\"node\"}",
"interval": "",
"legendFormat": "VRAM Used",
"refId": "A"
}
],
"title": "GPU VRAM Usage",
"type": "timeseries"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"max": 1,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.8
},
{
"color": "orange",
"value": 0.92
},
{
"color": "red",
"value": 0.95
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"id": 2,
"options": {
"orientation": "auto",
"reduceOptions": {
"values": false,
"fields": "",
"calcs": [
"lastNotNull"
]
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "8.0.0",
"targets": [
{
"expr": "llamacpp_kv_cache_usage_ratio",
"interval": "",
"legendFormat": "{{ model }}",
"refId": "A"
}
],
"title": "KV-Cache Utilization (Gauge)",
"type": "gauge"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "ms/token",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "ms"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"id": 3,
"options": {
"legend": {
"calcs": [
"mean",
"max"
],
"displayMode": "table",
"placement": "right"
},
"tooltip": {
"mode": "single"
}
},
"pluginVersion": "8.0.0",
"targets": [
{
"expr": "rate(llamacpp_time_predict_ms_sum[5m]) / rate(llamacpp_time_predict_ms_count[5m])",
"interval": "",
"legendFormat": "{{ model }}",
"refId": "A"
}
],
"title": "Prediction Latency by Model",
"type": "timeseries"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "Queue Size",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 3
},
{
"color": "red",
"value": 5
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"id": 4,
"options": {
"legend": {
"calcs": [
"mean",
"max"
],
"displayMode": "table",
"placement": "right"
},
"tooltip": {
"mode": "single"
}
},
"pluginVersion": "8.0.0",
"targets": [
{
"expr": "llamacpp_queue_size",
"interval": "",
"legendFormat": "{{ model }}",
"refId": "A"
}
],
"title": "Request Queue Depth",
"type": "timeseries"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "tokens/min",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"id": 5,
"options": {
"legend": {
"calcs": [
"mean"
],
"displayMode": "table",
"placement": "right"
},
"tooltip": {
"mode": "single"
}
},
"pluginVersion": "8.0.0",
"targets": [
{
"expr": "rate(llamacpp_tokens_predicted_total[1m]) * 60",
"interval": "",
"legendFormat": "{{ model }} (tokens/min)",
"refId": "A"
}
],
"title": "Token Generation Throughput",
"type": "timeseries"
},
{
"datasource": "Prometheus",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "Tokens",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "bars",
"fillOpacity": 100,
"gradientMode": "none",
"hideFrom": {
"tooltip": false,
"viz": false,
"legend": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"id": 6,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"pluginVersion": "8.0.0",
"targets": [
{
"expr": "histogram_quantile(0.95, rate(llamacpp_time_predict_ms_bucket[5m]))",
"interval": "",
"legendFormat": "p95 latency",
"refId": "A"
},
{
"expr": "histogram_quantile(0.99, rate(llamacpp_time_predict_ms_bucket[5m]))",
"interval": "",
"legendFormat": "p99 latency",
"refId": "B"
}
],
"title": "Latency Percentiles (p95, p99)",
"type": "timeseries"
}
],
"refresh": "30s",
"schemaVersion": 27,
"style": "dark",
"tags": [
"llm",
"llama-swap",
"gpu-monitoring",
"ciro-luciotta"
],
"templating": {
"list": []
},
"time": {
"from": "now-24h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "llama-swap GPU/LLM Monitoring",
"uid": "llama-swap-monitor",
"version": 1
}