Deepseek V4 (#23882)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: fzyzcjy <ch271828n@outlook.com> Co-authored-by: ispobock <ispobaoke@gmail.com> Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu> Co-authored-by: yueming-yuan <yym022502@gmail.com> Co-authored-by: DarkSharpness <2040703891@qq.com> Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com> Co-authored-by: yhyang201 <yhyang201@users.noreply.github.com> Co-authored-by: yhyang201 <yhyang201@gmail.com> Co-authored-by: Qiaolin Yu <90088090+qiaolin-yu@users.noreply.github.com> Co-authored-by: Ethan (Yusheng) Su <11704492+yushengsu-thu@users.noreply.github.com> Co-authored-by: Mingyi <27337995+wisclmy0611@users.noreply.github.com> Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> Co-authored-by: Yihao Wang <42559837+againstentropy@users.noreply.github.com>
This commit is contained in:
co-authored by
Baizhou Zhang
Claude Opus 4.7
fzyzcjy
ispobock
Zhiqiang Xie
yueming-yuan
DarkSharpness
Yuhao Yang
yhyang201
yhyang201
Qiaolin Yu
Ethan Su
Mingyi
Cheng Wan
Yihao Wang
parent
55224fff08
commit
35870d55ac
@@ -13,6 +13,7 @@ ARG DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee
|
||||
ARG BUILD_AND_DOWNLOAD_PARALLEL=8
|
||||
ARG SGL_KERNEL_VERSION=0.4.2.post1
|
||||
ARG SGL_VERSION
|
||||
ARG SGL_DEEP_GEMM_VERSION=0.0.1
|
||||
ARG USE_LATEST_SGLANG=0
|
||||
ARG GDRCOPY_VERSION=2.5.1
|
||||
ARG PIP_DEFAULT_INDEX
|
||||
@@ -244,6 +245,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
| xargs -r python3 -m pip uninstall -y && \
|
||||
python3 -m pip install --index-url https://download.pytorch.org/whl/cu${CUINDEX} \
|
||||
torch torchvision torchaudio --force-reinstall; \
|
||||
python3 -m pip install https://github.com/sgl-project/whl/releases/download/v${SGL_DEEP_GEMM_VERSION}/sgl_deep_gemm-${SGL_DEEP_GEMM_VERSION}+cu129-py3-none-manylinux2014_$(uname -m).whl --force-reinstall; \
|
||||
fi \
|
||||
&& cd /sgl-workspace \
|
||||
&& rm -rf /tmp/sglang_deps \
|
||||
@@ -539,12 +541,20 @@ RUN --mount=type=cache,target=/root/.cache/pip \
|
||||
# the `nixl` import path) but unconditionally requires nixl-cu12, so we install
|
||||
# it with --no-deps and pair it with the matching nixl-cu12 / nixl-cu13 binary
|
||||
# to avoid shipping wrong-CUDA libs on cu13 images.
|
||||
# The upstream flash-mla packages are required for running deepseek-v4 models
|
||||
RUN --mount=type=cache,target=/root/.cache/pip if [ "${CUDA_VERSION%%.*}" = "12" ]; then \
|
||||
python3 -m pip install nixl nixl-cu12 --no-deps ; \
|
||||
python3 -m pip install cuda-python==12.9 ; \
|
||||
cd /sgl-workspace && git clone https://github.com/deepseek-ai/FlashMLA.git flash-mla \
|
||||
&& cd flash-mla && git submodule update --init --recursive \
|
||||
&& pip install --no-build-isolation -v . ; \
|
||||
elif [ "${CUDA_VERSION%%.*}" = "13" ]; then \
|
||||
python3 -m pip install nixl nixl-cu13 --no-deps ; \
|
||||
python3 -m pip install cuda-python==13.2.0 ; \
|
||||
cd /sgl-workspace && git clone https://github.com/deepseek-ai/FlashMLA.git flash-mla \
|
||||
&& ln -s /usr/local/cuda/include/cccl/cuda /usr/local/cuda/include/cuda \
|
||||
&& cd flash-mla && git submodule update --init --recursive \
|
||||
&& pip install --no-build-isolation -v . ; \
|
||||
fi
|
||||
|
||||
# Add yank script
|
||||
|
||||
Reference in New Issue
Block a user