From 539c2e192bb8030d80c6163ef03bf73f92644587 Mon Sep 17 00:00:00 2001
From: zhihang <zhihang161013@outlook.com>
Date: Tue, 22 Oct 2024 09:01:40 +0000
Subject: [PATCH] feat: add component 'vllm'

---
 vllm/0.6.3/24.03-lts/Dockerfile | 70 +++++++++++++++++++++++++++++++++
 vllm/meta.yml                   |  3 ++
 2 files changed, 73 insertions(+)
 create mode 100644 vllm/0.6.3/24.03-lts/Dockerfile
 create mode 100644 vllm/meta.yml

diff --git a/vllm/0.6.3/24.03-lts/Dockerfile b/vllm/0.6.3/24.03-lts/Dockerfile
new file mode 100644
index 00000000..95986ab8
--- /dev/null
+++ b/vllm/0.6.3/24.03-lts/Dockerfile
@@ -0,0 +1,70 @@
+# This vLLM Dockerfile is used to construct image that can build and run vLLM on x86 CPU platform.
+
+FROM openeuler/openeuler:24.03-lts AS cpu-test-1
+
+ENV CCACHE_DIR=/root/.cache/ccache
+
+ENV CMAKE_CXX_COMPILER_LAUNCHER=ccache
+
+RUN --mount=type=cache,target=/var/cache/yum \
+    yum update -y \
+    && yum install -y curl ccache git wget vim numactl gcc g++ python3-devel python3-pip gperftools-libs numactl-libs numactl-devel \
+    && yum install -y ffmpeg libSM libXext mesa-libGL \
+    && update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
+
+# https://intel.github.io/intel-extension-for-pytorch/cpu/latest/tutorials/performance_tuning/tuning_guide.html
+# intel-openmp provides additional performance improvement vs. openmp
+# tcmalloc provides better memory allocation efficiency, e.g, holding memory in caches to speed up access of commonly-used objects.
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip3 install intel-openmp
+
+ENV LD_PRELOAD="/usr/lib64/libtcmalloc_minimal.so.4:/usr/local/lib/libiomp5.so"
+
+RUN echo 'ulimit -c 0' >> ~/.bashrc
+
+RUN pip3 install intel_extension_for_pytorch==2.4.0
+
+WORKDIR /workspace
+
+RUN git clone https://github.com/vllm-project/vllm.git
+
+ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
+ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip3 install --upgrade pip && \
+    pip install -r vllm/requirements-build.txt
+
+# install oneDNN
+RUN git clone -b rls-v3.5 https://github.com/oneapi-src/oneDNN.git
+
+RUN --mount=type=cache,target=/root/.cache/ccache \
+    cmake -B ./oneDNN/build -S ./oneDNN -G Ninja -DONEDNN_LIBRARY_TYPE=STATIC \ 
+    -DONEDNN_BUILD_DOC=OFF \ 
+    -DONEDNN_BUILD_EXAMPLES=OFF \ 
+    -DONEDNN_BUILD_TESTS=OFF \ 
+    -DONEDNN_BUILD_GRAPH=OFF \ 
+    -DONEDNN_ENABLE_WORKLOAD=INFERENCE \ 
+    -DONEDNN_ENABLE_PRIMITIVE=MATMUL && \
+    cmake --build ./oneDNN/build --target install --config Release
+
+FROM cpu-test-1 AS build
+
+WORKDIR /workspace/vllm
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install -v -r requirements-cpu.txt
+
+# Support for building with non-AVX512 vLLM: docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" ...
+ARG VLLM_CPU_DISABLE_AVX512
+ENV VLLM_CPU_DISABLE_AVX512=${VLLM_CPU_DISABLE_AVX512}
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=cache,target=/root/.cache/ccache \
+    VLLM_TARGET_DEVICE=cpu python3 setup.py bdist_wheel && \
+    pip install dist/*.whl && \
+    rm -rf dist
+
+WORKDIR /workspace/
+
+RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
+
+ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
\ No newline at end of file
diff --git a/vllm/meta.yml b/vllm/meta.yml
new file mode 100644
index 00000000..f7f81620
--- /dev/null
+++ b/vllm/meta.yml
@@ -0,0 +1,3 @@
+0.6.3-oe2403lts:
+  path: vllm/0.6.3/24.03-lts/Dockerfile
+  arch: x86_64
\ No newline at end of file
-- 
Gitee