diff --git a/docker/Dockerfile b/docker/Dockerfile index acb9a06f1..76e6ba2ef 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -98,11 +98,11 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip setuptools wheel html5li # Download NVSHMEM source files -# We use Tom's DeepEP fork for GB200 for now +# We use Tom's DeepEP fork for GB200 for now; the 1fd57b0276311d035d16176bb0076426166e52f3 commit is https://github.com/fzyzcjy/DeepEP/tree/gb200_blog_part_2 RUN wget https://developer.download.nvidia.com/compute/redist/nvshmem/3.3.9/source/nvshmem_src_cuda12-all-all-3.3.9.tar.gz && \ if [ "$GRACE_BLACKWELL" = "1" ]; then \ git clone https://github.com/fzyzcjy/DeepEP.git \ - && cd DeepEP && git checkout 2555874d8713ea758671867a50ebc9883552686d && sed -i 's/#define NUM_CPU_TIMEOUT_SECS 100/#define NUM_CPU_TIMEOUT_SECS 1000/' csrc/kernels/configs.cuh && cd .. ; \ + && cd DeepEP && git checkout 1fd57b0276311d035d16176bb0076426166e52f3 && sed -i 's/#define NUM_CPU_TIMEOUT_SECS 100/#define NUM_CPU_TIMEOUT_SECS 1000/' csrc/kernels/configs.cuh && cd .. ; \ else \ git clone https://github.com/deepseek-ai/DeepEP.git \ && cd DeepEP && git checkout ${DEEPEP_COMMIT} && sed -i 's/#define NUM_CPU_TIMEOUT_SECS 100/#define NUM_CPU_TIMEOUT_SECS 1000/' csrc/kernels/configs.cuh && cd .. ; \