Files

Komal Kumar Teru ba871fb788 [Misc] support arbitrary MM datasets in spec dec bench (#33486 )

Signed-off-by: kkt-cohere <komal@cohere.com>
Signed-off-by: Komal Kumar Teru <162363718+kkt-cohere@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

2026-02-02 08:49:48 +00:00

cli.md

[Misc] support arbitrary MM datasets in spec dec bench (#33486 )

2026-02-02 08:49:48 +00:00

dashboard.md

Update CPU doc according to feedback (#32963 )

2026-01-24 16:02:44 +00:00

README.md

[Doc] Reorganize benchmark docs (#29658 )

2025-11-28 17:19:25 +08:00

sweeps.md

[Bugfix] Fix inconsistent handling of cache reset (#33481 )

2026-01-31 20:23:41 -08:00

README.md

Benchmark Suites

vLLM provides comprehensive benchmarking tools for performance testing and evaluation:

Benchmark CLI: vllm bench CLI tools and specialized benchmark scripts for interactive performance testing.
Parameter Sweeps: Automate vllm bench runs for multiple configurations, useful for optimization and tuning.
Performance Dashboard: Automated CI that publishes benchmarks on each commit.