xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 05:34:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Doc] update installation guide regarding aarch64+cuda pytorch build (#28875)

Browse Source 
Signed-off-by: Qidong Su <soodoshll@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Qidong Su 2025-11-20 22:40:25 -05:00 committed by GitHub
parent 0730414999
commit 698024ecce
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 4 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
docker/Dockerfile
View File

@ -56,7 +56,6 @@ ARG UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
# PyTorch provides its own indexes for standard and nightly builds
ARG PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly
# PIP supports multiple authentication schemes, including keyring
# By parameterizing the PIP_KEYRING_PROVIDER variable and setting it to
@ -98,7 +97,6 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ARG PYTORCH_CUDA_INDEX_BASE_URL
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
# Activate virtual environment and add uv to PATH
@ -317,7 +315,6 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ARG PYTORCH_CUDA_INDEX_BASE_URL
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
# Install uv for faster pip installs
@ -337,20 +334,6 @@ ENV UV_LINK_MODE=copy
# or future versions of triton.
RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
# arm64 (GH200) build follows the practice of "use existing pytorch" build,
# we need to install torch and torchvision from the nightly builds first,
# pytorch will not appear as a vLLM dependency in all of the following steps
# after this step
RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
uv pip install --system \
--index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
"torch==2.8.0.dev20250318+cu128" "torchvision==0.22.0.dev20250319" ; \
uv pip install --system \
--index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
--pre pytorch_triton==3.3.0+gitab727c40 ; \
fi
# 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/uv \

7
docs/deployment/docker.md
View File

@ -82,8 +82,7 @@ DOCKER_BUILDKIT=1 docker build . \
## 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.
A docker container can be built for aarch64 systems such as the Nvidia Grace-Hopper. At time of this writing, this 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=`
@ -94,7 +93,6 @@ of PyTorch Nightly and should be considered **experimental**. Using the flag `--
```bash
# Example of building on Nvidia GH200 server. (Memory usage: ~15GB, Build time: ~1475s / ~25 min, Image size: 6.93GB)
python3 use_existing_torch.py
DOCKER_BUILDKIT=1 docker build . \
--file docker/Dockerfile \
--target vllm-openai \
@ -102,7 +100,8 @@ of PyTorch Nightly and should be considered **experimental**. Using the flag `--
-t vllm/vllm-gh200-openai:latest \
--build-arg max_jobs=66 \
--build-arg nvcc_threads=2 \
--build-arg torch_cuda_arch_list="9.0 10.0+PTX"
--build-arg torch_cuda_arch_list="9.0 10.0+PTX" \
--build-arg RUN_WHEEL_CHECK=false
```
!!! note

5
docs/getting_started/installation/gpu.cuda.inc.md
View File

@ -158,10 +158,7 @@ uv pip install -e .
##### Use an existing PyTorch installation
There are scenarios where the PyTorch dependency cannot be easily installed with `uv`, e.g.:
- Building vLLM with PyTorch nightly or a custom PyTorch build.
- Building vLLM with aarch64 and CUDA (GH200), where the PyTorch wheels are not available on PyPI. Currently, only the PyTorch nightly has wheels for aarch64 with CUDA. You can run `uv pip install --index-url https://download.pytorch.org/whl/nightly/cu128 torch torchvision torchaudio` to [install PyTorch nightly](https://pytorch.org/get-started/locally/) and then build vLLM on top of it.
There are scenarios where the PyTorch dependency cannot be easily installed with `uv`, for example, when building vLLM with non-default PyTorch builds (like nightly or a custom build).
To build vLLM using an existing PyTorch installation: