root
aa55634571
litellm-health: added GPU fleet topology table, model routing map, 3-tier GPU checks (reachability, VRAM, temp, test inference) litellm-self-heal: added GPU fleet reference, rules for GPU unreachable and model not responding Infrastructure topology now fully documented: - amdpve: Strix Halo CPU (35B, 16 threads, 262K ctx, llama-server) - llm-gpu: RTX 3090 24GB (Dense tier) - ocu-llm: RTX 5070 12GB (MoE + Light tiers)
3.8 KiB
3.8 KiB
kind, name, description
| kind | name | description |
|---|---|---|
| function | check-litellm-health | Verifies LiteLLM deployment is healthy by checking admin UI, API docs, OIDC auth endpoint, container status, and aggregate health on the backend host. Designed as a reusable contract for any Syslog agent. |
Parameters
- public_url: string — The public LiteLLM URL (default: "https://litellm.sysloggh.net")
- backend_host: string — Internal CT host to check containers (default: "192.168.68.116")
- auth_host: string — Authentik server for OIDC (default: "192.168.68.11")
- gpu_hosts: array — GPU inference hosts to check (default: ["192.168.68.8", "192.168.68.110", "192.168.68.15"])
Returns
- overall_status: "healthy" | "degraded" | "down"
- checks: array of { name: string, status: string, detail: string }
- timestamp: string — ISO timestamp of the check run
- duration_ms: number — How long the check took
Requires
- SSH key access to backend_host for container checks
- Network access to public_url and auth_host
- curl and openssl available on the execution host
Ensures
- Each check returns a clear pass/fail status with detail message
- If any endpoint returns non-200, overall_status is "degraded"
- If backend host unreachable or >2 containers down, overall_status is "down"
- If /health/unified reports any non-healthy components, status reflects it
- Checks cover at minimum: admin UI, API docs, OIDC, containers, unified health, nginx proxy
GPU Fleet Topology
| Host | IP | Hardware | Models Served | Engine |
|---|---|---|---|---|
| llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | gemma-4-12b (Dense) | llama-server Docker |
| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | qwen3.6-27B-code (MoE), all Light tier | llama-server Docker |
| amdpve | 192.168.68.15 | AMD Strix Halo (CPU-only, -ngl 0) | ornith-1.0-35b (35B) | llama-server bare-metal |
Model Routing (LiteLLM → Router → GPU)
| Model Request | Router Routes To |
|---|---|
gemma-4-12b |
GPU_DENSE_URL → 192.168.68.8:8080 |
qwen3.6-27B-code |
GPU_MOE_URL → 192.168.68.110:8080 |
ornith-1.0-35b |
Router routes to 192.168.68.15:8080 |
syslog-auto |
Auto-routed by router tier logic |
Execution
- Read parameters — Use provided values or defaults
- Check public endpoints:
- GET {{public_url}}/ui/ → expect 200 ("LiteLLM Dashboard")
- GET {{public_url}}/docs → expect 200 ("LiteLLM API - Swagger UI")
- GET {{public_url}}/openapi.json → expect 200 (valid JSON, 497 paths)
- GET {{public_url}}/redoc → expect 200 ("LiteLLM API - ReDoc")
- Check nginx-proxied endpoints (internal only — Netbird routes to LiteLLM directly):
- GET http://{{backend_host}}/litellm/ui/ → expect 200
- GET http://{{backend_host}}/litellm/docs → expect 200
- Check aggregate health endpoint:
- GET {{backend_host}}:9000/health/unified → expect 200, check all components
- Check backend container health:
- SSH to {{backend_host}} →
docker ps→ verify all 6 containers are healthy - Containers: harness-litellm, harness-nginx, harness-router, harness-postgres, harness-redis, harness-dashboard
- SSH to {{backend_host}} →
- Check GPU fleet health:
- For each {{gpu_hosts}}:
- SSH or nvidia-smi check → verify GPU is reachable
- Check VRAM usage (warn if >90%)
- Check temperature (warn if >80°C)
- Verify model responds to a small test prompt
- For each {{gpu_hosts}}:
- Check model inference — Send test prompt to each model via LiteLLM API:
- POST /v1/chat/completions with model name → expect 200 + valid response
- Record token counts for baseline performance
- Check OIDC auth endpoint:
- Verify auth.sysloggh.net resolves to {{auth_host}}
- GET https://auth.sysloggh.net/ → expect login page
- Compile and report — Determine overall_status from individual check results