zhrrr 68c09efc37

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165) ...

Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>

2025-11-11 12:00:31 -05:00

..

lm-eval-harness

Disable nm-testing models with issues in CI (#28206)

2025-11-06 06:19:07 -08:00

performance-benchmarks

[CI/Build][Intel] Enable performance benchmarks for Intel Gaudi 3 (#26919)

2025-10-31 07:57:22 +08:00

scripts

[Build] Fix release pipeline failing annotation (#28272)

2025-11-07 10:06:45 -08:00

check-wheel-size.py

[CI] Raise VLLM_MAX_SIZE_MB to 500 due to failing Build wheel - CUDA 12.9 (#26722)

2025-10-14 10:52:05 -07:00

generate_index.py

…

release-pipeline.yaml

Remove the tpu docker image nightly build. (#27997)

2025-11-04 00:35:54 +00:00

test-amd.yaml

[BugFix] Add test_outputs.py to CI pipeline (#28466)

2025-11-11 16:01:30 +00:00

test-pipeline.yaml

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165)

2025-11-11 12:00:31 -05:00