WIP: [CI/Build] simplify Dockerfile build for ARM64 / GH200 (#11212)

Signed-off-by: drikster80 <ed.sealing@gmail.com>
Co-authored-by: drikster80 <ed.sealing@gmail.com>

Dockerfile

@@ -11,6 +11,7 @@ ARG CUDA_VERSION=12.4.1
 FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04 AS base
 ARG CUDA_VERSION=12.4.1
 ARG PYTHON_VERSION=3.12
+ARG TARGETPLATFORM
 ENV DEBIAN_FRONTEND=noninteractive
 
 # Install Python and other dependencies
@@ -46,9 +47,14 @@ WORKDIR /workspace
 # install build and runtime dependencies
 COPY requirements-common.txt requirements-common.txt
 COPY requirements-cuda.txt requirements-cuda.txt
+COPY requirements-cuda-arm64.txt requirements-cuda-arm64.txt
 RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install -r requirements-cuda.txt
 
+RUN --mount=type=cache,target=/root/.cache/pip \
+    if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
+        python3 -m pip install -r requirements-cuda-arm64.txt; \
+    fi
 
 # cuda arch list used by torch
 # can be useful for both `dev` and `test`
@@ -63,6 +69,7 @@ ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches}
 
 #################### WHEEL BUILD IMAGE ####################
 FROM base AS build
+ARG TARGETPLATFORM
 
 # install build dependencies
 COPY requirements-build.txt requirements-build.txt
@@ -70,6 +77,11 @@ COPY requirements-build.txt requirements-build.txt
 RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install -r requirements-build.txt
 
+RUN --mount=type=cache,target=/root/.cache/pip \
+    if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
+        python3 -m pip install -r requirements-cuda-arm64.txt; \
+    fi
+
 COPY . .
 ARG GIT_REPO_CHECK=0
 RUN --mount=type=bind,source=.git,target=.git \
@@ -134,8 +146,8 @@ COPY requirements-test.txt requirements-test.txt
 COPY requirements-dev.txt requirements-dev.txt
 RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install -r requirements-dev.txt
-
 #################### DEV IMAGE ####################
+
 #################### vLLM installation IMAGE ####################
 # image with vLLM installed
 FROM nvidia/cuda:${CUDA_VERSION}-base-ubuntu22.04 AS vllm-base
@@ -143,6 +155,9 @@ ARG CUDA_VERSION=12.4.1
 ARG PYTHON_VERSION=3.12
 WORKDIR /vllm-workspace
 ENV DEBIAN_FRONTEND=noninteractive
+ARG TARGETPLATFORM
+
+COPY requirements-cuda-arm64.txt requirements-cuda-arm64.txt
 
 RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
     echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment
@@ -168,18 +183,25 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
 # or future versions of triton.
 RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
 
-# install vllm wheel first, so that torch etc will be installed
+# Install vllm wheel first, so that torch etc will be installed.
 RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
     --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install dist/*.whl --verbose
 
 RUN --mount=type=cache,target=/root/.cache/pip \
-    . /etc/environment && \
-    python3 -m pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.6/flashinfer-0.1.6+cu121torch2.4-cp${PYTHON_VERSION_STR}-cp${PYTHON_VERSION_STR}-linux_x86_64.whl
+    if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
+        pip uninstall -y torch && \
+        python3 -m pip install -r requirements-cuda-arm64.txt; \
+    fi
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+. /etc/environment && \
+if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
+    python3 -m pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.6/flashinfer-0.1.6+cu121torch2.4-cp${PYTHON_VERSION_STR}-cp${PYTHON_VERSION_STR}-linux_x86_64.whl; \
+fi
 COPY examples examples
 #################### vLLM installation IMAGE ####################
 
-
 #################### TEST IMAGE ####################
 # image to run unit testing suite
 # note that this uses vllm installed by `pip`
@@ -209,7 +231,6 @@ COPY vllm/v1 /usr/local/lib/python3.12/dist-packages/vllm/v1
 RUN mkdir test_docs
 RUN mv docs test_docs/
 RUN mv vllm test_docs/
-
 #################### TEST IMAGE ####################
 
 #################### OPENAI API SERVER ####################
@@ -218,8 +239,11 @@ FROM vllm-base AS vllm-openai
 
 # install additional dependencies for openai api server
 RUN --mount=type=cache,target=/root/.cache/pip \
-    pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.0' timm==0.9.10
-
+    if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
+        pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10'; \
+    else \
+        pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.0' 'timm==0.9.10'; \
+    fi
 ENV VLLM_USAGE_SOURCE production-docker-image
 
 ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]

docs/source/serving/deploying_with_docker.rst

@@ -37,6 +37,32 @@ You can build and run vLLM from source via the provided `Dockerfile <https://git
         current GPU type the machine is running on, you can add the argument ``--build-arg torch_cuda_arch_list=""``
         for vLLM to find the current GPU type and build for that.
 
+Building for Arm64/aarch64
+--------------------------
+
+A docker container can be built for aarch64 systems such as the Nvidia Grace-Hopper. At time of this writing, this requires the use
+of PyTorch Nightly and should be considered **experimental**. Using the flag `--platform "linux/arm64"` will attempt to build for arm64.
+
+.. note::
+
+        Multiple modules must be compiled, so this process can take a while. Recommend using `--build-arg max_jobs=` & `--build-arg nvcc_threads=`
+        flags to speed up build process. However, ensure your 'max_jobs' is substantially larger than 'nvcc_threads' to get the most benefits.
+        Keep an eye on memory usage with parallel jobs as it can be substantial (see example below).
+
+.. code-block:: console
+
+    # Example of building on Nvidia GH200 server. (Memory usage: ~12GB, Build time: ~1475s / ~25 min, Image size: 7.26GB)
+    $ DOCKER_BUILDKIT=1 sudo docker build . \
+      --target vllm-openai \
+      -platform "linux/arm64" \
+      -t vllm/vllm-gh200-openai:latest \
+      --build-arg max_jobs=66 \
+      --build-arg nvcc_threads=2 \
+      --build-arg torch_cuda_arch_list="9.0+PTX" \
+      --build-arg vllm_fa_cmake_gpu_arches="90-real"
+
+
+
 
 To run vLLM:
 

requirements-build.txt

@@ -4,6 +4,6 @@ ninja
 packaging
 setuptools>=61
 setuptools-scm>=8
-torch==2.5.1
+torch==2.5.1; platform_machine != 'aarch64'
 wheel
 jinja2

requirements-cuda-arm64.txt

+--index-url https://download.pytorch.org/whl/nightly/cu124
+torchvision==0.22.0.dev20241215; platform_machine == 'aarch64'
+torch==2.6.0.dev20241210+cu124; platform_machine == 'aarch64'

requirements-cuda.txt

@@ -4,7 +4,7 @@
 # Dependencies for NVIDIA GPUs
 ray >= 2.9
 nvidia-ml-py >= 12.560.30 # for pynvml package
-torch == 2.5.1
+torch == 2.5.1; platform_machine != 'aarch64'
 # These must be updated alongside torch
-torchvision == 0.20.1 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
+torchvision == 0.20.1; platform_machine != 'aarch64' # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
 xformers == 0.0.28.post3; platform_system == 'Linux' and platform_machine == 'x86_64'  # Requires PyTorch 2.5.1