Ethan FengandGitHub b7f9b6ab27 [Metrics] Add group-aware KV cache capacity to vllm:cache_config_info (#42206) ...

The startup log already reports the correct group-aware KV cache capacity for
hybrid models, but Prometheus did not expose matching info in 'vllm:cache_config_info`.

This PR adds kv_cache_size_tokens and kv_cache_max_concurrency.

Signed-off-by: Ethan Feng <ethan.fengch@gmail.com>

2026-06-12 11:49:44 +00:00

..

__init__.py

[Refactor] Move serve entrypoint tests under tests/entrypoints/serve/ (#37595)

2026-03-20 02:10:47 -07:00

test_basic.py

[Refactor] Move serve entrypoint tests under tests/entrypoints/serve/ (#37595)

2026-03-20 02:10:47 -07:00

test_metrics.py

[Metrics] Add group-aware KV cache capacity to vllm:cache_config_info (#42206)

2026-06-12 11:49:44 +00:00

test_optional_middleware.py

fix: add API key authorization to /v2 endpoints (#42594)

2026-05-16 01:29:27 +00:00

test_orca_metrics.py

[Refactor] Move serve entrypoint tests under tests/entrypoints/serve/ (#37595)

2026-03-20 02:10:47 -07:00