EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[Bugfix] Fix Qwen3/DSV3/DSV3.2 model support (#11510)

Browse Source
This commit is contained in:
Even Zhou
2025-10-16 15:14:09 +08:00
committed by GitHub
parent b0d20cdec7
commit 3cceaa381a
12 changed files with 102 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docker/Dockerfile.npu
View File

@@ -6,12 +6,13 @@ ARG PYTHON_VERSION=py3.11
FROM quay.io/ascend/cann:$CANN_VERSION-$DEVICE_TYPE-$OS-$PYTHON_VERSION
# Update pip & apt sources
ARG DEVICE_TYPE
ARG PIP_INDEX_URL="https://pypi.org/simple/"
ARG APTMIRROR=""
ARG MEMFABRIC_URL=https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/mf_adapter-1.0.0-cp311-cp311-linux_aarch64.whl
ARG PYTORCH_VERSION=2.6.0
ARG TORCHVISION_VERSION=0.21.0
ARG PTA_URL="https://gitee.com/ascend/pytorch/releases/download/v7.1.0.1-pytorch2.6.0/torch_npu-2.6.0.post1-cp311-cp311-manylinux_2_28_aarch64.whl"
ARG PTA_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/ops/torch_npu-2.6.0.post2%2Bgit95d6260-cp311-cp311-linux_aarch64.whl"
ARG VLLM_TAG=v0.8.5
ARG TRITON_ASCEND_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/triton_ascend-3.2.0%2Bgitb0ea0850-cp311-cp311-linux_aarch64.whl"
ARG BISHENG_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/Ascend-BiSheng-toolkit_aarch64.run"
@@ -71,7 +72,7 @@ RUN git clone --depth 1 https://github.com/vllm-project/vllm.git --branch $VLLM_
# TODO: install from pypi released triton-ascend
RUN pip install torch==$PYTORCH_VERSION torchvision==$TORCHVISION_VERSION --index-url https://download.pytorch.org/whl/cpu --no-cache-dir \
&& wget ${PTA_URL} && pip install "./torch_npu-2.6.0.post1-cp311-cp311-manylinux_2_28_aarch64.whl" --no-cache-dir \
&& wget ${PTA_URL} && pip install "./torch_npu-2.6.0.post2+git95d6260-cp311-cp311-linux_aarch64.whl" --no-cache-dir \
&& python3 -m pip install --no-cache-dir attrs==24.2.0 numpy==1.26.4 scipy==1.13.1 decorator==5.1.1 psutil==6.0.0 pytest==8.3.2 pytest-xdist==3.6.1 pyyaml pybind11 \
&& pip install ${TRITON_ASCEND_URL} --no-cache-dir
@@ -92,6 +93,13 @@ RUN pip install wheel==0.45.1 && git clone --branch $SGLANG_KERNEL_NPU_TAG http
&& cd .. && rm -rf sgl-kernel-npu \
&& cd "$(pip show deep-ep | awk '/^Location:/ {print $2}')" && ln -s deep_ep/deep_ep_cpp*.so
# Install CustomOps
RUN wget https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/ops/CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run && \
chmod a+x ./CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run && \
./CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run --quiet --install-path=/usr/local/Ascend/ascend-toolkit/latest/opp && \
wget https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/ops/custom_ops-1.0.$DEVICE_TYPE-cp311-cp311-linux_aarch64.whl && \
pip install ./custom_ops-1.0.$DEVICE_TYPE-cp311-cp311-linux_aarch64.whl
# Install Bisheng
RUN wget ${BISHENG_URL} && chmod a+x Ascend-BiSheng-toolkit_aarch64.run && ./Ascend-BiSheng-toolkit_aarch64.run --install && rm Ascend-BiSheng-toolkit_aarch64.run