20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Use CUDA 12.4 as default for release and nightly wheels (#12098)

Browse Source
This commit is contained in:
Michael Goin 2025-02-26 22:06:37 -05:00 committed by GitHub
parent a31614e386
commit ca377cf1b9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 25 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
.buildkite/release-pipeline.yaml
View File

@ -1,4 +1,15 @@
steps:
- label: "Build wheel - CUDA 12.4"
agents:
queue: cpu_queue_postmerge
commands:
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.4.0 --tag vllm-ci:build-image --target build --progress plain ."
- "mkdir artifacts"
- "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
- "bash .buildkite/upload-wheels.sh"
env:
DOCKER_BUILDKIT: "1"
- label: "Build wheel - CUDA 12.1"
agents:
queue: cpu_queue_postmerge
@ -37,7 +48,7 @@ steps:
queue: cpu_queue_postmerge
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.1.0 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain ."
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.4.0 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain ."
- "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
- label: "Build and publish TPU release image"

10
.buildkite/upload-wheels.sh
View File

@ -50,8 +50,11 @@ aws s3 cp "$normal_wheel" "s3://vllm-wheels/$BUILDKITE_COMMIT/"
if [[ $normal_wheel == *"cu118"* ]]; then
# if $normal_wheel matches cu118, do not upload the index.html
echo "Skipping index files for cu118 wheels"
elif [[ $normal_wheel == *"cu121"* ]]; then
# if $normal_wheel matches cu121, do not upload the index.html
echo "Skipping index files for cu121 wheels"
else
# only upload index.html for cu12 wheels (default wheels)
# only upload index.html for cu124 wheels (default wheels)
aws s3 cp index.html "s3://vllm-wheels/$BUILDKITE_COMMIT/vllm/index.html"
aws s3 cp "s3://vllm-wheels/nightly/index.html" "s3://vllm-wheels/$BUILDKITE_COMMIT/index.html"
fi
@ -63,8 +66,11 @@ aws s3 cp "$normal_wheel" "s3://vllm-wheels/nightly/"
if [[ $normal_wheel == *"cu118"* ]]; then
# if $normal_wheel matches cu118, do not upload the index.html
echo "Skipping index files for cu118 wheels"
elif [[ $normal_wheel == *"cu121"* ]]; then
# if $normal_wheel matches cu121, do not upload the index.html
echo "Skipping index files for cu121 wheels"
else
# only upload index.html for cu12 wheels (default wheels)
# only upload index.html for cu124 wheels (default wheels)
aws s3 cp index.html "s3://vllm-wheels/nightly/vllm/index.html"
fi

4
docs/source/getting_started/installation/gpu/cuda.inc.md
View File

@ -23,12 +23,12 @@ Therefore, it is recommended to install vLLM with a **fresh new** environment. I
You can install vLLM using either `pip` or `uv pip`:
```console
# Install vLLM with CUDA 12.1.
# Install vLLM with CUDA 12.4.
pip install vllm # If you are using pip.
uv pip install vllm # If you are using uv.
```
As of now, vLLM's binaries are compiled with CUDA 12.1 and public PyTorch release versions by default. We also provide vLLM binaries compiled with CUDA 11.8 and public PyTorch release versions:
As of now, vLLM's binaries are compiled with CUDA 12.4 and public PyTorch release versions by default. We also provide vLLM binaries compiled with CUDA 12.1, 11.8, and public PyTorch release versions:
```console
# Install vLLM with CUDA 11.8.

7
setup.py
View File

@ -54,7 +54,7 @@ elif (sys.platform.startswith("linux") and torch.version.cuda is None
# fallback to cpu
VLLM_TARGET_DEVICE = "cpu"
MAIN_CUDA_VERSION = "12.1"
MAIN_CUDA_VERSION = "12.4"
def is_sccache_available() -> bool:
@ -571,9 +571,8 @@ def get_requirements() -> List[str]:
cuda_major, cuda_minor = torch.version.cuda.split(".")
modified_requirements = []
for req in requirements:
if ("vllm-flash-attn" in req
and not (cuda_major == "12" and cuda_minor == "1")):
# vllm-flash-attn is built only for CUDA 12.1.
if ("vllm-flash-attn" in req and cuda_major != "12"):
# vllm-flash-attn is built only for CUDA 12.x.
# Skip for other versions.
continue
modified_requirements.append(req)