Create Dockerfile

Dockerfile

@@ -0,0 +1,77 @@
+######################### BASE IMAGE #########################
+FROM ubuntu:22.04 AS base
+
+WORKDIR /workspace/
+
+ARG PYTHON_VERSION=3.12
+ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
+
+ENV LD_PRELOAD=""
+
+# Install minimal dependencies and uv
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    apt-get update -y \
+    && apt-get install -y --no-install-recommends ccache git curl wget ca-certificates \
+        gcc-12 g++-12 libtcmalloc-minimal4 libnuma-dev ffmpeg libsm6 libxext6 libgl1 \
+    && update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12 \
+    && curl -LsSf https://astral.sh/uv/install.sh | sh
+
+RUN git clone --branch v0.8.5.post1 https://github.com/vllm-project/vllm.git /workspace/vllm
+
+ENV CCACHE_DIR=/root/.cache/ccache
+ENV CMAKE_CXX_COMPILER_LAUNCHER=ccache
+
+ENV PATH="/root/.local/bin:$PATH"
+ENV VIRTUAL_ENV="/opt/venv"
+ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
+RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+ENV UV_HTTP_TIMEOUT=500
+
+# Install Python dependencies 
+ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
+ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
+ENV UV_INDEX_STRATEGY="unsafe-best-match"
+ENV UV_LINK_MODE="copy"
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install --upgrade pip && \
+    uv pip install -r /workspace/vllm/requirements/cpu.txt
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install intel-openmp==2024.2.1 intel_extension_for_pytorch==2.6.0
+
+ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so:$LD_PRELOAD"
+
+RUN echo 'ulimit -c 0' >> ~/.bashrc
+
+######################### BUILD IMAGE #########################
+FROM base AS vllm-build
+
+ARG GIT_REPO_CHECK=0
+# 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}
+
+WORKDIR /workspace/vllm
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install -r /workspace/vllm/requirements/build.txt
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=cache,target=/root/.cache/ccache \
+    VLLM_TARGET_DEVICE=cpu python3 setup.py bdist_wheel 
+
+
+######################### RELEASE IMAGE #########################
+FROM base AS vllm-openai
+
+WORKDIR /workspace/
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=cache,target=/root/.cache/ccache \
+    --mount=type=bind,from=vllm-build,src=/workspace/vllm/dist,target=dist \
+    uv pip install dist/*.whl
+
+ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]