diff --git a/.github/workflows/release-docker-npu-nightly.yml b/.github/workflows/release-docker-npu-nightly.yml index df5db619d..b5e565119 100644 --- a/.github/workflows/release-docker-npu-nightly.yml +++ b/.github/workflows/release-docker-npu-nightly.yml @@ -74,6 +74,6 @@ jobs: push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }} provenance: false build-args: | - SGLANG_KERNEL_NPU_TAG=2026.01.28 + SGLANG_KERNEL_NPU_TAG=2026.02.01.post2 CANN_VERSION=${{ matrix.cann_version }} DEVICE_TYPE=${{ matrix.device_type }} diff --git a/docker/npu.Dockerfile b/docker/npu.Dockerfile index fd526649f..937a0de14 100644 --- a/docker/npu.Dockerfile +++ b/docker/npu.Dockerfile @@ -93,9 +93,9 @@ RUN git clone https://github.com/sgl-project/sglang --branch $SGLANG_TAG && \ RUN ${PIP_INSTALL} wheel==0.45.1 pybind11 pyyaml decorator scipy attrs psutil \ && mkdir sgl-kernel-npu \ && cd sgl-kernel-npu \ - && wget https://github.com/sgl-project/sgl-kernel-npu/releases/download/${SGLANG_KERNEL_NPU_TAG}/sgl-kernel-npu-${SGLANG_KERNEL_NPU_TAG}-${CANN_VERSION}-${DEVICE_TYPE}-$(arch).zip \ - && unzip sgl-kernel-npu-${SGLANG_KERNEL_NPU_TAG}-${CANN_VERSION}-${DEVICE_TYPE}-$(arch).zip \ - && ${PIP_INSTALL} output/deep_ep*.whl output/sgl_kernel_npu*.whl \ + && wget https://github.com/sgl-project/sgl-kernel-npu/releases/download/${SGLANG_KERNEL_NPU_TAG}/sgl-kernel-npu-${SGLANG_KERNEL_NPU_TAG}-torch2.8.0-py311-cann${CANN_VERSION}-${DEVICE_TYPE}-$(arch).zip \ + && unzip sgl-kernel-npu-${SGLANG_KERNEL_NPU_TAG}-torch2.8.0-py311-cann${CANN_VERSION}-${DEVICE_TYPE}-$(arch).zip \ + && ${PIP_INSTALL} deep_ep*.whl sgl_kernel_npu*.whl \ && cd .. && rm -rf sgl-kernel-npu \ && cd "$(python3 -m pip show deep-ep | awk '/^Location:/ {print $2}')" && ln -sf deep_ep/deep_ep_cpp*.so