Mirrors/modelscope
1
0
Fork 0
mirror of https://github.com/modelscope/modelscope.git synced 2026-08-29 10:08:40 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update npu dockerfile (#1736)

Browse Source
This commit is contained in:
addsubmuldiv
2026-06-15 11:07:56 +08:00
committed by GitHub
parent c7dba8de1e
commit c1d88e6ab7
4 changed files with 389 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
docker/Dockerfile.ascend
View File

@@ -3,7 +3,8 @@ FROM {base_image}
ENV PIP_DISABLE_PIP_VERSION_CHECK=1 \
PIP_DEFAULT_TIMEOUT=300 \
PIP_RETRIES=10 \
SOC_VERSION={soc_version}
SOC_VERSION={soc_version} \
CANN_VERSION={cann_version}
SHELL ["/bin/bash", "-c"]
@@ -36,15 +37,15 @@ RUN ARCH=$(uname -m) && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
# Install torch & torch_npu & torchvision
pip install torch==2.9.0 torch_npu==2.9.0 torchvision==0.24.0 && \
pip install torch==2.9.0 torch_npu==2.9.0.post2 torchvision==0.24.0 && \
# Install vllm
cd vllm && VLLM_TARGET_DEVICE=empty pip install -v -e . && cd .. && \
# Install vllm-ascend
cd vllm-ascend && pip install -v -e . && cd ..
# ---------- Clone training-side repositories ----------
RUN git clone --depth 1 --branch v0.15.3 https://github.com/NVIDIA/Megatron-LM.git /Megatron-LM && \
git clone --depth 1 --branch core_r0.15.3 https://gitcode.com/Ascend/MindSpeed.git /MindSpeed && \
RUN git clone --depth 1 --branch {megatron_branch} https://github.com/NVIDIA/Megatron-LM.git /Megatron-LM && \
git clone --depth 1 --branch {mindspeed_branch} https://gitcode.com/Ascend/MindSpeed.git /MindSpeed && \
GIT_LFS_SKIP_SMUDGE=1 git clone --depth 1 -b {swift_branch} --single-branch https://github.com/modelscope/ms-swift.git /ms-swift && \
git clone --depth 1 https://github.com/modelscope/mcore-bridge.git /mcore-bridge
@@ -70,7 +71,7 @@ RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
torch==2.9.0 torchvision==0.24.0 torchaudio==2.9.0; \
fi && \
pip install --no-cache-dir --force-reinstall --no-deps \
torch_npu==2.9.0 && \
torch_npu==2.9.0.post2 && \
rm -rf /root/.cache/pip
# ---------- Remove CUDA-only dependencies pulled in by vllm (they cause missing libtorch_cuda.so errors on NPU) ----------
@@ -122,6 +123,37 @@ RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
pip install --no-cache-dir omegaconf==2.3.0 && \
pip cache purge
# ---------- Reinstall triton-ascend for the selected CANN version ----------
RUN set -eux; \
pip uninstall -y triton || true; \
pip uninstall -y triton-ascend || true; \
case "${CANN_VERSION}" in \
8.5.*) \
pip install --no-cache-dir --force-reinstall triton-ascend==3.2.0; \
;; \
9.0.0) \
PY_ABI="cp$(python -c 'import sys; print(f"{sys.version_info.major}{sys.version_info.minor}")')"; \
case "${PY_ABI}" in \
cp310|cp311|cp312|cp313) ;; \
*) echo "Unsupported Python ABI for triton-ascend 3.2.1: ${PY_ABI}" >&2; exit 1 ;; \
esac; \
ARCH="$(uname -m)"; \
case "${ARCH}" in \
aarch64|x86_64) ;; \
*) echo "Unsupported architecture for triton-ascend 3.2.1: ${ARCH}" >&2; exit 1 ;; \
esac; \
WHEEL_NAME="triton_ascend-3.2.1-${PY_ABI}-${PY_ABI}-manylinux_2_27_${ARCH}.manylinux_2_28_${ARCH}.whl"; \
WHEEL_PATH="/tmp/${WHEEL_NAME}"; \
curl -fL "https://gitcode.com/Ascend/triton-ascend/releases/download/v3.2.1/${WHEEL_NAME}" -o "${WHEEL_PATH}"; \
pip install --no-cache-dir --force-reinstall "${WHEEL_PATH}"; \
rm -f "${WHEEL_PATH}"; \
;; \
*) \
echo "Unsupported CANN_VERSION for triton-ascend install: ${CANN_VERSION}" >&2; \
exit 1; \
;; \
esac
RUN echo 'source /usr/local/Ascend/ascend-toolkit/set_env.sh' >> /root/.bashrc && \
echo '[ -f /usr/local/Ascend/nnal/atb/set_env.sh ] && source /usr/local/Ascend/nnal/atb/set_env.sh' >> /root/.bashrc && \
echo 'set +H' >> /root/.bashrc