Skip to content

Commit e46d95f

Browse files
WANDY666WANDY666
committed
Merge branch 'main' of https://github.com/ModelTC/LightLLM into dp_kv_fetch
2 parents c7e5b81 + a41492e commit e46d95f

File tree

207 files changed

+8802
-1225
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

207 files changed

+8802
-1225
lines changed

‎docker/cuda_version_12.6.1/Dockerfile‎

Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,48 @@
1+
ARG CUDA_VERSION=12.6.1
2+
FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu22.04
3+
ARG PYTHON_VERSION=3.10
4+
ARG MAMBA_VERSION=24.7.1-0
5+
ARG TARGETPLATFORM
6+
ENV PATH=/opt/conda/bin:$PATH \
7+
CONDA_PREFIX=/opt/conda
8+
9+
RUN chmod 777 -R /tmp && apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
10+
ca-certificates \
11+
libssl-dev \
12+
curl \
13+
g++ \
14+
make \
15+
git && \
16+
rm -rf /var/lib/apt/lists/*
17+
18+
RUN case ${TARGETPLATFORM} in \
19+
"linux/arm64") MAMBA_ARCH=aarch64 ;; \
20+
*) MAMBA_ARCH=x86_64 ;; \
21+
esac && \
22+
curl -fsSL -o ~/mambaforge.sh "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh" && \
23+
bash ~/mambaforge.sh -b -p /opt/conda && \
24+
rm ~/mambaforge.sh
25+
26+
RUN case ${TARGETPLATFORM} in \
27+
"linux/arm64") exit 1 ;; \
28+
*) /opt/conda/bin/conda update -y conda && \
29+
/opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
30+
esac && \
31+
/opt/conda/bin/conda clean -ya
32+
33+
34+
WORKDIR /root
35+
36+
COPY ./requirements.txt /lightllm/requirements.txt
37+
RUN pip install -U pip
38+
RUN pip install -r /lightllm/requirements.txt --no-cache-dir
39+
40+
RUN pip install --no-cache-dir vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
41+
42+
# TODO: offline compile
43+
# RUN git clone https://github.com/ModelTC/LightKernel.git && cd LightKernel && pip install --no-deps -v .
44+
45+
RUN apt-get update && apt-get install -y libnuma-dev # for sgl_kernel
46+
47+
COPY . /lightllm
48+
RUN pip install -e /lightllm --no-cache-dir

‎docker/cuda_version_12.6.1/Dockerfile.deepep‎

Lines changed: 84 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
1+
ARG CUDA_VERSION=12.6.1
2+
FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu22.04
3+
ARG PYTHON_VERSION=3.10
4+
ARG MAMBA_VERSION=24.7.1-0
5+
ARG TARGETPLATFORM
6+
ENV PATH=/opt/conda/bin:$PATH \
7+
CONDA_PREFIX=/opt/conda
8+
9+
RUN chmod 777 -R /tmp && apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
10+
ca-certificates \
11+
libssl-dev \
12+
curl \
13+
g++ \
14+
make \
15+
git && \
16+
rm -rf /var/lib/apt/lists/*
17+
18+
RUN case ${TARGETPLATFORM} in \
19+
"linux/arm64") MAMBA_ARCH=aarch64 ;; \
20+
*) MAMBA_ARCH=x86_64 ;; \
21+
esac && \
22+
curl -fsSL -o ~/mambaforge.sh "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh" && \
23+
bash ~/mambaforge.sh -b -p /opt/conda && \
24+
rm ~/mambaforge.sh
25+
26+
RUN case ${TARGETPLATFORM} in \
27+
"linux/arm64") exit 1 ;; \
28+
*) /opt/conda/bin/conda update -y conda && \
29+
/opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
30+
esac && \
31+
/opt/conda/bin/conda clean -ya
32+
33+
34+
WORKDIR /root
35+
36+
COPY ./requirements.txt /lightllm/requirements.txt
37+
RUN pip install -U pip
38+
RUN pip install -r /lightllm/requirements.txt --no-cache-dir
39+
40+
RUN pip install --no-cache-dir vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
41+
42+
# TODO: offline compile
43+
# RUN git clone https://github.com/ModelTC/LightKernel.git && cd LightKernel && pip install --no-deps -v .
44+
45+
RUN apt-get update && apt-get install -y libnuma-dev wget devscripts debhelper dh-make build-essential dkms
46+
RUN apt-get install -y ibverbs-providers infiniband-diags perftest rdma-core libibverbs-dev librdmacm-dev
47+
48+
ENV CUDA_HOME=/usr/local/cuda \
49+
GDRCOPY_HOME=/usr/src/gdrdrv-2.4.4/
50+
51+
RUN mkdir -p /tmp/gdrcopy && cd /tmp \
52+
&& git clone https://github.com/NVIDIA/gdrcopy.git -b v2.4.4 \
53+
&& cd gdrcopy/packages \
54+
&& CUDA=/usr/local/cuda ./build-deb-packages.sh \
55+
&& dpkg -i gdrdrv-dkms_*.deb libgdrapi_*.deb gdrcopy-tests_*.deb gdrcopy_*.deb \
56+
&& cd / && rm -rf /tmp/gdrcopy
57+
58+
# Fix DeepEP IBGDA symlink
59+
RUN ln -sf /usr/lib/x86_64-linux-gnu/libmlx5.so.1 /usr/lib/x86_64-linux-gnu/libmlx5.so
60+
61+
RUN wget https://developer.download.nvidia.com/compute/redist/nvshmem/3.3.9/source/nvshmem_src_cuda12-all-all-3.3.9.tar.gz \
62+
&& tar -xf nvshmem_src_cuda12-all-all-3.3.9.tar.gz && mv nvshmem_src nvshmem \
63+
&& cd nvshmem \
64+
&& rm -f /root/nvshmem_src_cuda12-all-all-3.3.9.tar.gz \
65+
&& NVSHMEM_SHMEM_SUPPORT=0 \
66+
NVSHMEM_UCX_SUPPORT=0 \
67+
NVSHMEM_USE_NCCL=0 \
68+
NVSHMEM_MPI_SUPPORT=0 \
69+
NVSHMEM_IBGDA_SUPPORT=1 \
70+
NVSHMEM_PMIX_SUPPORT=0 \
71+
NVSHMEM_TIMEOUT_DEVICE_POLLING=0 \
72+
NVSHMEM_USE_GDRCOPY=1 \
73+
cmake -S . -B build/ -DCMAKE_INSTALL_PREFIX=/root/nvshmem/install -DCMAKE_CUDA_ARCHITECTURES=90 \
74+
&& cmake --build build --target install -j64
75+
76+
ARG DEEPEP_COMMIT=b6ce310bb0b75079682d09bc2ebc063a074fbd58
77+
RUN git clone https://github.com/deepseek-ai/DeepEP.git && cd DeepEP && git checkout ${DEEPEP_COMMIT} && cd ..
78+
79+
WORKDIR /root/DeepEP
80+
ENV NVSHMEM_DIR=/root/nvshmem/install
81+
RUN NVSHMEM_DIR=/root/nvshmem/install python setup.py install
82+
83+
COPY . /lightllm
84+
RUN pip install -e /lightllm --no-cache-dir

‎docker/cuda_version_12.6.1/Dockerfile.nixl‎

Lines changed: 94 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,94 @@
1+
ARG CUDA_VERSION=12.6.1
2+
FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu22.04
3+
ARG PYTHON_VERSION=3.10
4+
ARG MAMBA_VERSION=24.7.1-0
5+
ARG TARGETPLATFORM
6+
ENV PATH=/opt/conda/bin:$PATH \
7+
CONDA_PREFIX=/opt/conda
8+
9+
RUN chmod 777 -R /tmp && apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
10+
ca-certificates \
11+
libssl-dev \
12+
curl \
13+
g++ \
14+
make \
15+
git && \
16+
rm -rf /var/lib/apt/lists/*
17+
18+
RUN case ${TARGETPLATFORM} in \
19+
"linux/arm64") MAMBA_ARCH=aarch64 ;; \
20+
*) MAMBA_ARCH=x86_64 ;; \
21+
esac && \
22+
curl -fsSL -o ~/mambaforge.sh -v "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh" && \
23+
bash ~/mambaforge.sh -b -p /opt/conda && \
24+
rm ~/mambaforge.sh
25+
26+
RUN case ${TARGETPLATFORM} in \
27+
"linux/arm64") exit 1 ;; \
28+
*) /opt/conda/bin/conda update -y conda && \
29+
/opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
30+
esac && \
31+
/opt/conda/bin/conda clean -ya
32+
33+
34+
WORKDIR /root
35+
36+
COPY ./requirements.txt /lightllm/requirements.txt
37+
RUN --mount=type=cache,target=/root/.cache/pip pip install -r /lightllm/requirements.txt --ignore-installed --extra-index-url https://download.pytorch.org/whl/cu124
38+
39+
RUN --mount=type=cache,target=/root/.cache/pip pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
40+
RUN --mount=type=cache,target=/root/.cache/pip git clone https://github.com/ModelTC/LightKernel.git && cd LightKernel && pip install --no-deps -v .
41+
42+
RUN apt-get update && apt-get install -y libnuma-dev wget devscripts debhelper dh-make build-essential dkms
43+
RUN apt-get install -y ibverbs-providers infiniband-diags perftest rdma-core libibverbs-dev librdmacm-dev
44+
45+
ENV CUDA_HOME=/usr/local/cuda \
46+
GDRCOPY_HOME=/usr/src/gdrdrv-2.4.4/
47+
48+
RUN mkdir -p /tmp/gdrcopy && cd /tmp \
49+
&& git clone https://github.com/NVIDIA/gdrcopy.git -b v2.4.4 \
50+
&& cd gdrcopy/packages \
51+
&& CUDA=/usr/local/cuda ./build-deb-packages.sh \
52+
&& dpkg -i gdrdrv-dkms_*.deb libgdrapi_*.deb gdrcopy-tests_*.deb gdrcopy_*.deb \
53+
&& cd / && rm -rf /tmp/gdrcopy
54+
55+
RUN apt-get update && apt-get install -y cmake automake autotools-dev libtool libz-dev && \
56+
DEBIAN_FRONTEND=noninteractive apt-get -y install --reinstall libibverbs-dev rdma-core ibverbs-utils libibumad-dev; \
57+
rm -rf /usr/lib/ucx && \
58+
rm -rf /opt/hpcx/ucx && \
59+
cd /usr/local/src && \
60+
git clone https://github.com/openucx/ucx.git && \
61+
cd ucx && \
62+
git checkout v1.19.x && \
63+
./autogen.sh && ./configure \
64+
--enable-shared \
65+
--disable-static \
66+
--disable-doxygen-doc \
67+
--enable-optimizations \
68+
--enable-cma \
69+
--enable-devel-headers \
70+
--with-cuda=/usr/local/cuda \
71+
--with-verbs=yes \
72+
--with-dm \
73+
--with-gdrcopy=/usr/local \
74+
--with-efa \
75+
--enable-mt && \
76+
make -j && \
77+
make -j install-strip && \
78+
ldconfig;
79+
80+
RUN apt-get update && apt-get install -y pkg-config tmux net-tools ; \
81+
cd /usr/local/src; \
82+
pip install --upgrade meson pybind11 patchelf; \
83+
git clone https://github.com/ai-dynamo/nixl.git -b main && \
84+
cd nixl && \
85+
rm -rf build && \
86+
mkdir build && \
87+
meson setup build/ --prefix=/usr/local/nixl --buildtype=release && \
88+
cd build && \
89+
ninja && \
90+
ninja install && \
91+
cd .. && pip install . --no-deps;
92+
93+
COPY . /lightllm
94+
RUN pip install -e /lightllm --no-cache-dir

‎docker/cuda_version_12.6.1/Dockerfile.nixl.deepep‎

Lines changed: 121 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,121 @@
1+
ARG CUDA_VERSION=12.6.1
2+
FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu22.04
3+
4+
ARG PYTHON_VERSION=3.10
5+
ARG MAMBA_VERSION=24.7.1-0
6+
ARG TARGETPLATFORM
7+
8+
ENV PATH=/opt/conda/bin:$PATH \
9+
CONDA_PREFIX=/opt/conda
10+
11+
RUN chmod 777 -R /tmp && apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
12+
ca-certificates \
13+
libssl-dev \
14+
curl \
15+
g++ \
16+
make \
17+
git && \
18+
rm -rf /var/lib/apt/lists/*
19+
20+
RUN case ${TARGETPLATFORM} in \
21+
"linux/arm64") MAMBA_ARCH=aarch64 ;; \
22+
*) MAMBA_ARCH=x86_64 ;; \
23+
esac && \
24+
curl -fsSL -o ~/mambaforge.sh -v "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh" && \
25+
bash ~/mambaforge.sh -b -p /opt/conda && \
26+
rm ~/mambaforge.sh
27+
28+
RUN case ${TARGETPLATFORM} in \
29+
"linux/arm64") exit 1 ;; \
30+
*) /opt/conda/bin/conda update -y conda && \
31+
/opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
32+
esac && \
33+
/opt/conda/bin/conda clean -ya
34+
35+
36+
WORKDIR /root
37+
38+
COPY ./requirements.txt /lightllm/requirements.txt
39+
RUN --mount=type=cache,target=/root/.cache/pip pip install -r /lightllm/requirements.txt --ignore-installed --extra-index-url https://download.pytorch.org/whl/cu124
40+
41+
RUN --mount=type=cache,target=/root/.cache/pip pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
42+
RUN --mount=type=cache,target=/root/.cache/pip git clone https://github.com/ModelTC/LightKernel.git && cd LightKernel && pip install --no-deps -v .
43+
44+
RUN apt-get update && apt-get install -y libnuma-dev wget devscripts debhelper dh-make build-essential dkms
45+
RUN apt-get install -y ibverbs-providers infiniband-diags perftest rdma-core libibverbs-dev librdmacm-dev
46+
47+
ENV CUDA_HOME=/usr/local/cuda \
48+
GDRCOPY_HOME=/usr/src/gdrdrv-2.4.4/
49+
50+
RUN mkdir -p /tmp/gdrcopy && cd /tmp \
51+
&& git clone https://github.com/NVIDIA/gdrcopy.git -b v2.4.4 \
52+
&& cd gdrcopy/packages \
53+
&& CUDA=/usr/local/cuda ./build-deb-packages.sh \
54+
&& dpkg -i gdrdrv-dkms_*.deb libgdrapi_*.deb gdrcopy-tests_*.deb gdrcopy_*.deb \
55+
&& cd / && rm -rf /tmp/gdrcopy
56+
57+
# Fix DeepEP IBGDA symlink
58+
RUN ln -sf /usr/lib/x86_64-linux-gnu/libmlx5.so.1 /usr/lib/x86_64-linux-gnu/libmlx5.so
59+
60+
RUN wget https://developer.download.nvidia.com/compute/redist/nvshmem/3.3.9/source/nvshmem_src_cuda12-all-all-3.3.9.tar.gz \
61+
&& tar -xf nvshmem_src_cuda12-all-all-3.3.9.tar.gz && mv nvshmem_src nvshmem \
62+
&& cd nvshmem \
63+
&& rm -f /root/nvshmem_src_cuda12-all-all-3.3.9.tar.gz \
64+
&& NVSHMEM_SHMEM_SUPPORT=0 \
65+
NVSHMEM_UCX_SUPPORT=0 \
66+
NVSHMEM_USE_NCCL=0 \
67+
NVSHMEM_MPI_SUPPORT=0 \
68+
NVSHMEM_IBGDA_SUPPORT=1 \
69+
NVSHMEM_PMIX_SUPPORT=0 \
70+
NVSHMEM_TIMEOUT_DEVICE_POLLING=0 \
71+
NVSHMEM_USE_GDRCOPY=1 \
72+
cmake -S . -B build/ -DCMAKE_INSTALL_PREFIX=/root/nvshmem/install -DCMAKE_CUDA_ARCHITECTURES=90 \
73+
&& cmake --build build --target install -j64
74+
75+
ARG DEEPEP_COMMIT=b6ce310bb0b75079682d09bc2ebc063a074fbd58
76+
RUN git clone https://github.com/deepseek-ai/DeepEP.git && cd DeepEP && git checkout ${DEEPEP_COMMIT} && cd ..
77+
78+
WORKDIR /root/DeepEP
79+
ENV NVSHMEM_DIR=/root/nvshmem/install
80+
RUN NVSHMEM_DIR=/root/nvshmem/install python setup.py install
81+
82+
RUN apt-get update && apt-get install -y cmake automake autotools-dev libtool libz-dev && \
83+
DEBIAN_FRONTEND=noninteractive apt-get -y install --reinstall libibverbs-dev rdma-core ibverbs-utils libibumad-dev; \
84+
rm -rf /usr/lib/ucx && \
85+
rm -rf /opt/hpcx/ucx && \
86+
cd /usr/local/src && \
87+
git clone https://github.com/openucx/ucx.git && \
88+
cd ucx && \
89+
git checkout v1.19.x && \
90+
./autogen.sh && ./configure \
91+
--enable-shared \
92+
--disable-static \
93+
--disable-doxygen-doc \
94+
--enable-optimizations \
95+
--enable-cma \
96+
--enable-devel-headers \
97+
--with-cuda=/usr/local/cuda \
98+
--with-verbs=yes \
99+
--with-dm \
100+
--with-gdrcopy=/usr/local \
101+
--with-efa \
102+
--enable-mt && \
103+
make -j && \
104+
make -j install-strip && \
105+
ldconfig;
106+
107+
RUN apt-get update && apt-get install -y pkg-config tmux net-tools ; \
108+
cd /usr/local/src; \
109+
pip install --upgrade meson pybind11 patchelf; \
110+
git clone https://github.com/ai-dynamo/nixl.git -b main && \
111+
cd nixl && \
112+
rm -rf build && \
113+
mkdir build && \
114+
meson setup build/ --prefix=/usr/local/nixl --buildtype=release && \
115+
cd build && \
116+
ninja && \
117+
ninja install && \
118+
cd .. && pip install . --no-deps;
119+
120+
COPY . /lightllm
121+
RUN pip install -e /lightllm --no-cache-dir

0 commit comments

Comments
 (0)