xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 10:34:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update docker docs with ARM CUDA cross-compile (#19037)

Browse Source 
Signed-off-by: mgoin <michael@neuralmagic.com>
This commit is contained in:
Michael Goin 2025-06-03 04:21:53 -04:00 committed by GitHub
parent f32fcd9444
commit 6d18ed2a2e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
docs/deployment/docker.md
View File

@ -107,10 +107,21 @@ DOCKER_BUILDKIT=1 docker build . \
-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 torch_cuda_arch_list="9.0 10.0+PTX" \
--build-arg vllm_fa_cmake_gpu_arches="90-real"
```
!!! note
If you are building the `linux/arm64` image on a non-ARM host (e.g., an x86_64 machine), you need to ensure your system is set up for cross-compilation using QEMU. This allows your host machine to emulate ARM64 execution.
Run the following command on your host machine to register QEMU user static handlers:
```console
docker run --rm --privileged multiarch/qemu-user-static --reset -p yes
```
After setting up QEMU, you can use the `--platform "linux/arm64"` flag in your `docker build` command.
## Use the custom-built vLLM Docker image
To run vLLM with the custom-built Docker image: