Hiroken. 6450b536a6 [Bugfix] Fix E2E latency calculation and add warmup support in mm_processor benchmark (#32646) ...

Signed-off-by: Hongjian Zhang <zhanghongjian@xiaohongshu.com>
Signed-off-by: Xingran Wang <wangxingran123456@outlook.com>
Signed-off-by: Hiroken. <105287758+HirokenOvo@users.noreply.github.com>
Co-authored-by: Xingran Wang <wangxingran123456@outlook.com>

2026-01-24 10:31:41 +00:00

..

lib

[Benchmark] Don't default to temperature==0 in vllm bench serve (#32723)

2026-01-22 10:03:15 +00:00

sweep

[Benchmark][Bugfix] Fix race condtion when starting server for sweep benchmark (#32927)

2026-01-23 12:11:18 +00:00

__init__.py

Fix Python packaging edge cases (#17159)

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

datasets.py

feat: spec decode with draft models (#24322)

2026-01-19 16:05:46 -05:00

latency.py

[Misc] support nsys profile for bench latency (#29776)

2025-12-18 14:52:20 +00:00

mm_processor.py

[Bugfix] Fix E2E latency calculation and add warmup support in mm_processor benchmark (#32646)

2026-01-24 10:31:41 +00:00

serve.py

[Benchmark] Don't default to temperature==0 in vllm bench serve (#32723)

2026-01-22 10:03:15 +00:00

startup.py

resolve pydantic error in startup benchmark (#31348)

2026-01-10 02:41:27 +00:00

throughput.py

Add Multimodal Processor Benchmark (#29105)

2026-01-01 19:26:53 -08:00