-
-
Couldn't load subscription status.
- Fork 10.8k
[Bugfix] Avoid to warmup when world size is 1 #5442
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
Conversation
Signed-off-by: kerthcet <[email protected]>
Signed-off-by: kerthcet <[email protected]>
|
I agree with the idea, but why this PR touches so many lines? You just need to avoid the warmup if world size > 1. |
|
Ok, got your idea about avoid warmup once worldsize is 1, what I did here is slightly different. Will modify as you suggested. |
Signed-off-by: kerthcet <[email protected]>
|
Done |
|
can you revert the format change? let's keep the pr clean on what is changed. |
This reverts commit ed4f36b.
Signed-off-by: kerthcet <[email protected]>
5e53a9f to
3fba472
Compare
Make sense to me, I used to make them separate commits. Anyway, reverted. |
Signed-off-by: kerthcet <[email protected]>
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.
Thanks for addressing my comments! It can be merged once it passed all the tests.
|
Thanks for the quick reply. |
|
It's weird, the test |
|
Seems we totally removed the warmup in #5293, can I know the reason here? @youkaichao |
|
oh, I just happen to remove the warmup because I don't want the warmup for world/tp/pp group. sorry for overwriting your PR! |
|
Make sense, seems we can close now. |
FILL IN THE PR DESCRIPTION HERE
xref: #4587
@youkaichao I have no env to test with the vGPU+vLLM, but at least we can avoid to warmup when the worldsize = 1, do you agree?
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,LLMclass, 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.shto 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-requiredand 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-requiredlabel 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!