Li, Jiang d34f5fe939 [Bugfix][CPU] Fallback oneDNN linear to torch linear to fix half gemm support on legecy platforms (#27526) ...

Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2025-10-27 23:25:44 -07:00

..

Dockerfile

Update PyTorch to 2.9.0+cu129 (#24994)

2025-10-21 17:20:18 -04:00

Dockerfile.cpu

[Bugfix][CPU] Fallback oneDNN linear to torch linear to fix half gemm support on legecy platforms (#27526)

2025-10-27 23:25:44 -07:00

Dockerfile.nightly_torch

[NVIDIA] [Perf] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#26714)

2025-10-16 16:20:25 -07:00

Dockerfile.ppc64le

[CI/Build] Fix ppc64le CPU build and tests (#22443)

2025-10-11 13:04:42 +08:00

Dockerfile.rocm

[CI/Build] Fix AMD import failures in CI (#26841)

2025-10-16 07:28:20 +00:00

Dockerfile.rocm_base

[ROCm] Update AITER branch for ROCm base docker (#27586)

2025-10-27 17:22:33 +00:00

Dockerfile.s390x

[CI/Build] Replace vllm.entrypoints.openai.api_server entrypoint with vllm serve command (#25967)

2025-10-02 10:04:57 -07:00

Dockerfile.tpu

Always use cache mounts when installing vllm to avoid populating pip cache in the image. Also remove apt cache. (#23270)

2025-08-21 18:01:03 -04:00

Dockerfile.xpu

[XPU] Upgrade NIXL to remove CUDA dependency (#26570)

2025-10-11 05:15:23 +00:00