[V1][Metrics] Add GPU cache usage % gauge (#12561)

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-01-30 02:31:01 +00:00
parent 1c1bb0bbf2
commit f17f1d4608
5 changed files with 18 additions and 2 deletions
--- a/tests/entrypoints/openai/test_metrics.py
+++ b/tests/entrypoints/openai/test_metrics.py
@@ -200,6 +200,7 @@ EXPECTED_METRICS = [
 EXPECTED_METRICS_V1 = [
    "vllm:num_requests_running",
    "vllm:num_requests_waiting",
+    "vllm:gpu_cache_usage_perc",
    "vllm:prompt_tokens_total",
    "vllm:generation_tokens_total",
    "vllm:request_prompt_tokens_sum",