[Core] Add Additional Metrics to vLLM Server#12726

Open

sahelib25 wants to merge 10 commits intovllm-project:mainfrom krai:add_metrics

+326-106

Commits on Feb 6, 2025

Commits on Feb 10, 2025

Commits on Feb 11, 2025

Fix vllm:total_tokens_in_queue metric.
sahelib25
committed

Commits on Feb 12, 2025

Fix tests and pre-commit issues.
sahelib25
committed

Commits on Feb 13, 2025

Log total GPU model load time (model weights loading+memory profiling+CUDA graph capture+engine initialization).
sahelib25
committed

Commits on Feb 14, 2025