Frank
d7bf9f119a
The frank-medium retirement tail the 2026-09-26 lucebox cutover left uncommitted: the radiance quadlet tree, its swap/fetch tooling and its seam test are deleted (archive copies live in dankserver/.AGENTTRASH/ 20260926-frank-medium-radiance/ and scripts/.AGENTTRASH/20260926- frank-medium-radiance/), the planner/allowlist/test-changed mappings drop the service, and frank-large's chat template moves to scripts/ (its old home was the retired frank-medium dir). Finished here: - tests/frank_primary_unit.bats: the lucebox quadlet seam (boot persistence, host-network bind, HIP_VISIBLE_DEVICES=0,1, HIP-reserved env-name guard, checkout-mounted entrypoint/healthcheck, first-start patience, deployer payload/port gates). - test-changed.sh: explicit .AGENTTRASH/ case — retirement commits move files to trash, and the wrapper refused those additions with "no focused-test mapping". - observability: the vllm: namespace left with the radiance runtime. Rules keep only llamacpp:* series (prefix-cache reuse, spec-decode, queueing, endpoint-down); the dashboard drops the vLLM KV/latency panels; prometheus.yml documents that frank-primary (lucebox) has no /metrics and therefore no scrape job. llm-fleet.json was left corrupted mid-edit (missing opening brace) and is rewritten from HEAD. Suite: 339 green (was 7 red).
218 lines
6.9 KiB
JSON
218 lines
6.9 KiB
JSON
{
|
|
"uid": "llm-fleet",
|
|
"title": "LLM fleet \u2014 capacity and reuse",
|
|
"description": "The signals that explain the LLM endpoints under load. One metric namespace: llamacpp:* for frank-small (Dankclaw, RTX 3090) and frank-large (Dankclaw, gfx1151 iGPU). frank-primary (Dankserver, the Lucebox DS4.1 engine since the 2026-09-26 cutover) exports no metrics and has no panels here. The endpoint picker selects between them. See serverAppConfigs-docs/Infrastructure/Observability.md for the namespace split and the addressability rules.",
|
|
"tags": [
|
|
"llm",
|
|
"capacity"
|
|
],
|
|
"timezone": "browser",
|
|
"schemaVersion": 39,
|
|
"version": 2,
|
|
"refresh": "30s",
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "job",
|
|
"label": "endpoint",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"query": {
|
|
"query": "label_values({__name__=~\"llamacpp:.*\"}, job)",
|
|
"refId": "A"
|
|
},
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "timeseries",
|
|
"title": "Prefix cache reuse rate",
|
|
"description": "rate(hits)/rate(queries) in tokens. The llama.cpp prompt counter EXCLUDES cached tokens (its own HELP line), so this divides by cached + prompt. High means pinned conversations are served from cache: measured 2026-09-20, an identical 13,021-token prompt went 2.30 s cold to 0.68 s warm with 9,888 tokens (76 %) reused.",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0,
|
|
"max": 1,
|
|
"custom": {
|
|
"fillOpacity": 10,
|
|
"lineWidth": 1
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "rate(llamacpp:prompt_tokens_cached_total{job=~\"$job\"}[5m]) / clamp_min(rate(llamacpp:prompt_tokens_cached_total{job=~\"$job\"}[5m]) + rate(llamacpp:prompt_tokens_total{job=~\"$job\"}[5m]), 0.001)",
|
|
"legendFormat": "{{job}} reuse (llama.cpp)",
|
|
"refId": "A"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "timeseries",
|
|
"title": "Speculative decoding (acceptance)",
|
|
"description": "The one failure no client can see: the drafter silently stops and the endpoint keeps answering at autoregressive speed. Accepted tokens per draft step, and the mean accepted length (1 + accepted/drafts, the recording rule job:llm_spec_accept_length:rate5m) \u2014 1.0 means the draft round is pure overhead.",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "rate(llamacpp:spec_decode_num_accepted_tokens_total{job=~\"$job\"}[5m]) / clamp_min(rate(llamacpp:spec_decode_num_drafts_total{job=~\"$job\"}[5m]), 0.001)",
|
|
"legendFormat": "{{job}} accepted per draft step",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "job:llm_spec_accept_length:rate5m{job=~\"$job\"}",
|
|
"legendFormat": "{{job}} mean accepted length (vLLM)",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "rate(llamacpp:spec_decode_num_draft_tokens_total{job=~\"$job\"}[5m])",
|
|
"legendFormat": "{{job}} draft tokens/s",
|
|
"refId": "C"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "timeseries",
|
|
"title": "Requests waiting (queue depth)",
|
|
"description": "llama.cpp: anything above zero means the engine is serialising (with --parallel 1 a second concurrent request always shows up here). vLLM: the scheduler's own waiting/running gauges against MAXSEQS=8.",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "llamacpp:requests_deferred{job=~\"$job\"}",
|
|
"legendFormat": "{{job}} deferred",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "llamacpp:requests_processing{job=~\"$job\"}",
|
|
"legendFormat": "{{job}} processing",
|
|
"refId": "B"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "timeseries",
|
|
"title": "Decode and prefill throughput",
|
|
"description": "llama.cpp: llamacpp:predicted_tokens_seconds is decode, llamacpp:prompt_tokens_seconds is prompt. vLLM: the token counters, rate'd. The series carry the job label of their scrape, so the endpoint picker selects between the runtimes.",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "llamacpp:predicted_tokens_seconds{job=~\"$job\"}",
|
|
"legendFormat": "{{job}} decode tok/s (llama.cpp)",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "llamacpp:prompt_tokens_seconds{job=~\"$job\"}",
|
|
"legendFormat": "{{job}} prefill tok/s (llama.cpp)",
|
|
"refId": "B"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 5,
|
|
"type": "timeseries",
|
|
"title": "Decode steps and batch size",
|
|
"description": "llama.cpp-only signal \u2014 vLLM does not publish per-step counters. Steps per second and the busy-slot count per step (the effective batch).",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "rate(llamacpp:n_decode_total{job=~\"$job\"}[5m])",
|
|
"legendFormat": "{{job}} decode steps/s",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "llamacpp:n_busy_slots_per_decode{job=~\"$job\"}",
|
|
"legendFormat": "{{job}} sequences per decode step",
|
|
"refId": "B"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 6,
|
|
"type": "timeseries",
|
|
"title": "Firing fleet alerts",
|
|
"description": "The LLM-fleet rules from shared/prometheus/rules/llm-fleet.yml. A firing alert is delivered to Signal: Prometheus -> Alertmanager (dankclaw quadlet) -> the host-side signal-relay user unit -> signal-cli, since 2026-09-17.",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "ALERTS{alertname=~\"Llm.*\", alertstate=\"firing\"}",
|
|
"legendFormat": "{{alertname}} {{job}}",
|
|
"refId": "A"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|