vllm/benchmarks/mm_processor.py · 6450b536a63d92d856d368c44c8d4250e31e2ea7 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Bugfix] Fix E2E latency calculation and add warmup support in mm_processor benchmark (#32646) · 6450b536

Hiroken. authored Jan 24, 2026

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>

6450b536

mm_processor.py 14.5 KB