diff --git a/cluster/applications/monitoring/values.yaml b/cluster/applications/monitoring/values.yaml index fcf46f7..4b4536e 100644 --- a/cluster/applications/monitoring/values.yaml +++ b/cluster/applications/monitoring/values.yaml @@ -232,15 +232,50 @@ prometheus: hostname: astro-orbiter gpu: rtx3090 - - job_name: llama-server-astro-orbiter + # Router exposes per-model Prometheus metrics via /metrics?model=. + # The old :8000 target (gemma-2-27b-it-GGUF) was removed after the day2 + # cutover (2026-08-12) to llama-server-router on :8002. Three separate + # jobs — one per model registered in the router — are used so each gets + # its own model label. The static `model` label is set to the canonical + # llama.cpp model id (the `id` field from /v1/models, not the alias). + - job_name: llama-server-astro-orbiter-qwen3 scrape_interval: 15s metrics_path: /metrics + params: + model: ["Qwen3.6-35B-A3B-UD-Q4_K_S"] static_configs: - targets: - - 10.1.71.130:8000 + - 10.1.71.130:8002 labels: hostname: astro-orbiter - model: bartowski/gemma-2-27b-it-GGUF + endpoint: astro-orbiter-router + model: Qwen3.6-35B-A3B-UD-Q4_K_S + + - job_name: llama-server-astro-orbiter-llama3 + scrape_interval: 15s + metrics_path: /metrics + params: + model: ["Meta-Llama-3.1-8B-Instruct-Q4_K_M"] + static_configs: + - targets: + - 10.1.71.130:8002 + labels: + hostname: astro-orbiter + endpoint: astro-orbiter-router + model: Meta-Llama-3.1-8B-Instruct-Q4_K_M + + - job_name: llama-server-astro-orbiter-phi35 + scrape_interval: 15s + metrics_path: /metrics + params: + model: ["Phi-3.5-mini-instruct-Q8_0"] + static_configs: + - targets: + - 10.1.71.130:8002 + labels: + hostname: astro-orbiter + endpoint: astro-orbiter-router + model: Phi-3.5-mini-instruct-Q8_0 # ─── Grafana ────────────────────────────────────────────────────────────────── grafana: