Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[SpecDecode] [Minor] Fix spec decode sampler tests #7183

Merged
merged 1 commit into from
Aug 6, 2024
Merged

[SpecDecode] [Minor] Fix spec decode sampler tests #7183

merged 1 commit into from
Aug 6, 2024

Conversation

LiuXiaoxuanPKU
Copy link
Collaborator

Sampler tests failed when number of GPUs > 1. This PR fixes this.

@github-actions GitHub Actions
Copy link

github-actions bot commented Aug 6, 2024

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which consists a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of default ones by unblocking the steps in your fast-check build on Buildkite UI.

Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge).

To run full CI, you can do one of these:

  • Comment /ready on the PR
  • Add ready label to the PR
  • Enable auto-merge.

🚀

@LiuXiaoxuanPKU
Copy link
Collaborator Author

/ready

@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Aug 6, 2024
DarkLight1337
DarkLight1337 reviewed Aug 6, 2024
View reviewed changes
tests/samplers/test_rejection_sampler.py
@@ -339,7 +339,7 @@ def __init__(self, vocab_size: int, rejection_sampler: RejectionSampler):
self.vocab_size = vocab_size
self.vocab_range = (0, vocab_size)

self.rejection_sampler.init_gpu_tensors(rank=0)
self.rejection_sampler.init_gpu_tensors(device=0)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should it be device=device here?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should it be device=device here?

there is no device in this class, so I assume all things happen on gpu 0, correct me if I'm wrong.

@LiuXiaoxuanPKU LiuXiaoxuanPKU merged commit 5c60c8c into vllm-project:main Aug 6, 2024
65 checks passed
sfc-gh-mkeralapura pushed a commit to sfc-gh-mkeralapura/vllm that referenced this pull request Aug 12, 2024
@LiuXiaoxuanPKU @sfc-gh-mkeralapura
[SpecDecode] [Minor] Fix spec decode sampler tests (vllm-project#7183)
798ecbe
kylesayrs pushed a commit to neuralmagic/vllm that referenced this pull request Aug 17, 2024
@LiuXiaoxuanPKU @kylesayrs
[SpecDecode] [Minor] Fix spec decode sampler tests (vllm-project#7183)
6f27c1b
fialhocoelho pushed a commit to opendatahub-io/vllm that referenced this pull request Aug 22, 2024
@LiuXiaoxuanPKU @fialhocoelho
[SpecDecode] [Minor] Fix spec decode sampler tests (vllm-project#7183)
a51647d
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@DarkLight1337 DarkLight1337 DarkLight1337 left review comments

@njhill njhill njhill approved these changes

@cadedaniel cadedaniel Awaiting requested review from cadedaniel

Assignees
No one assigned
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@LiuXiaoxuanPKU @njhill @DarkLight1337