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.

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

[Bugfix] Fix tensor parallel for qwen2 classification model #10297

Merged
merged 3 commits into from
Nov 14, 2024

Conversation

Isotr0py
Copy link
Collaborator

@Isotr0py Isotr0py commented Nov 13, 2024

  • Fix tensor parallel for Qwen2ForSequenceClassification

Signed-off-by: Isotr0py <2037008807@qq.com>
Copy link

👋 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 starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

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

🚀

Signed-off-by: Isotr0py <2037008807@qq.com>
@Isotr0py
Copy link
Collaborator Author

Let me see if this PR can fix #10218 (comment) as well...

@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 13, 2024
@DarkLight1337
Copy link
Member

Let me see if this PR can fix #10218 (comment) as well...

This change doesn't fix it.

@DarkLight1337 DarkLight1337 self-assigned this Nov 13, 2024
Signed-off-by: Isotr0py <2037008807@qq.com>
quant_config=quant_config)
quant_config=quant_config,
input_is_parallel=False,
bias=False,
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

I just found that qwen2_cls doesn't have bias in score layer. 😅

The test should pass with this change. (The debugging was terrible 😅)

Copy link
Member

Choose a reason for hiding this comment

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

Yeah it passes now. Let's fix the timeout in another PR.

@DarkLight1337 DarkLight1337 merged commit 15bb833 into vllm-project:main Nov 14, 2024
50 checks passed
@Isotr0py Isotr0py deleted the fix-qwen-cls branch November 14, 2024 02:56
omer-dayan pushed a commit to omer-dayan/vllm that referenced this pull request Nov 14, 2024
…ject#10297)

Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: OmerD <omer@run.ai>
sumitd2 pushed a commit to sumitd2/vllm that referenced this pull request Nov 14, 2024
…ject#10297)

Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Sumit Dubey <sumit.dubey2@ibm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants