-
-
Notifications
You must be signed in to change notification settings - Fork 5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[ROCm] Cleanup Dockerfile and remove outdated patch #6482
Conversation
👋 Hi! Thank you for contributing to the vLLM project. Full CI run is still required to merge this PR so once the PR is ready to go, please make sure to run it. If you need all test signals in between PR commits, you can trigger full CI as well. To run full CI, you can do one of these:
🚀 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
QQ: What is the motivation to discontinue the support for ROCm 5.7 and 6.0? I think previously some AMD folks said we should maintain 5.7 and 6.0 because some users can't freely update the system ROCm.
|
||
.. code-block:: console | ||
|
||
$ docker build -f Dockerfile.rocm -t vllm-rocm . | ||
$ DOCKER_BUILDKIT=1 docker build -f Dockerfile.rocm -t vllm-rocm . |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is this required?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Since the buildkite was introduced from vllm upstream, this is the easier way for me to get around the docker build errors.
Co-authored-by: Woosuk Kwon <[email protected]>
We would like to clean up those temp patches from vllm codebase, because bf16 patch was only needed for ROCm 6.0 and is fixed in ROCm 6.1, and hipify patch is only needed for ROCm 5.7. The hipify patch was removed by someone else already from vllm code base and no one seems to complain, maybe meaning no one is using the latest vllm for ROCm 5.7. Pretty soon there will be ROCm 6.2 upgrade. While it seems user-friendly to support more and more ROCm versions in one Dockerfile, but in reality, the CI is running on the latest/default ROCm version in the Dockerfile, and how we can guarantee that the older versions will continue to work with each commit from the upstream? Another note is that, we are working to make the release cleaner in the future and hopefully no longer need to have temp patches when a new ROCm version is released. Even when it is absolutely necessary, we will put the patch in a different location to download instead of putting them in the vllm code base. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I see. Makes sense. Thanks for the explanation!
Signed-off-by: Alvant <[email protected]>
This pull request is to clean up and simplify Dockerfile.rocm, remove outdated patch, and updated the documentation.
For users who want to use older versions of ROCm, please check vllm older commits or branches or tags.
FIX #xxxx (link existing issues this PR will resolve)
BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE
PR Checklist (Click to Expand)
Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.
PR Title and Classification
Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:
[Bugfix]
for bug fixes.[CI/Build]
for build or continuous integration improvements.[Doc]
for documentation fixes and improvements.[Model]
for adding a new model or improving an existing model. Model name should appear in the title.[Frontend]
For changes on the vLLM frontend (e.g., OpenAI API server,LLM
class, etc.)[Kernel]
for changes affecting CUDA kernels or other compute kernels.[Core]
for changes in the core vLLM logic (e.g.,LLMEngine
,AsyncLLMEngine
,Scheduler
, etc.)[Hardware][Vendor]
for hardware-specific changes. Vendor name should appear in the prefix (e.g.,[Hardware][AMD]
).[Misc]
for PRs that do not fit the above categories. Please use this sparingly.Note: If the PR spans more than one category, please include all relevant prefixes.
Code Quality
The PR need to meet the following code quality standards:
format.sh
to format your code.docs/source/
if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.Notes for Large Changes
Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with
rfc-required
and might not go through the PR.What to Expect for the Reviews
The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:
action-required
label on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.Thank You
Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!