Talor AbramovichandBenjamin Chislett 3cc328a4be [SpecDecode][Benchmark] Add SPEED-bench support to benchmarking CLI (#36029) ...

Signed-off-by: talora <talora@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

2026-04-15 12:00:07 -04:00

..

datasets

[SpecDecode][Benchmark] Add SPEED-bench support to benchmarking CLI (#36029)

2026-04-15 12:00:07 -04:00

lib

[Bugfix] Fix vllm bench serve to count multimodal tokens in "total input tokens" (#38654)

2026-04-14 11:00:40 +00:00

sweep

Stop bench CLI from recursively casting all configs to dict (#37559)

2026-03-19 14:04:03 +00:00

__init__.py

Fix Python packaging edge cases (#17159)

2025-04-26 06:15:07 +08:00

latency.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

mm_processor.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902)

2026-03-25 06:14:43 -07:00

plot.py

[Benchmarks] Plot benchmark timeline and requests statistics (#35220)

2026-02-26 02:17:43 -08:00

serve.py

[Bugfix] Fix vllm bench serve to count multimodal tokens in "total input tokens" (#38654)

2026-04-14 11:00:40 +00:00

startup.py

Measure encoder compile time seperate from llm backbone (#39240)

2026-04-14 10:52:49 -04:00

throughput.py

[Bugfix] Add missing ASRDataset import and CLI args in benchmarks/throughput.py (#38114)

2026-04-08 13:53:53 +00:00