From 0f291115bd322be91e7f646ec1be8fdeaddafdfe Mon Sep 17 00:00:00 2001 From: Frank Date: Wed, 16 Sep 2026 06:34:53 -0700 Subject: [PATCH] observability: name the prefix-cache series that actually exist vllm:prefix_cache_hit_rate does not exist in this build; the exported pair is vllm:prefix_cache_hits_total / vllm:prefix_cache_queries_total, whose rates give the hit rate. A comment naming a series nobody can query is worse than no comment. --- shared/prometheus/prometheus.yml | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/shared/prometheus/prometheus.yml b/shared/prometheus/prometheus.yml index 6272cbd..c9d0a01 100644 --- a/shared/prometheus/prometheus.yml +++ b/shared/prometheus/prometheus.yml @@ -57,9 +57,11 @@ scrape_configs: # LLM fleet. Scraped on the LAN addresses, not the guarded vhosts: these are # machine clients and Prometheus cannot solve an Anubis challenge. # frank-medium is vLLM, and its series are the ones that explain behaviour - # under load — vllm:kv_cache_usage_perc (how full the pool is), - # vllm:prefix_cache_hit_rate (whether pinned conversations are being reused), - # vllm:num_requests_waiting (queue depth), and the request-latency histograms. + # under load — vllm:kv_cache_usage_perc (how full the per-card pool is), + # vllm:num_requests_waiting (queue depth), the request-latency histograms, + # and the prefix-cache pair vllm:prefix_cache_hits_total over + # vllm:prefix_cache_queries_total (their rates give the hit rate, which says + # whether pinned conversations are actually being reused). # frank-large is llama.cpp and exposes throughput counters under llamacpp:. - job_name: "frank-medium" metrics_path: "/metrics"