Skip to content

[Model][LoRA]LoRA support added for Qwen #9622

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
Merged
merged 4 commits into from
Oct 29, 2024
Merged

[Model][LoRA]LoRA support added for Qwen #9622

merged 4 commits into from
Oct 29, 2024

Conversation

jeejeelee
Copy link
Collaborator

@jeejeelee jeejeelee commented Oct 23, 2024 •
edited by DarkLight1337
Loading

FILL IN THE PR DESCRIPTION HERE

FIX #3458
FIX #9584

Distinguish between Qwen LLM and VL to better support LoRA (similar treatment needed for ChatGLM as well). Currently set as WIP, the main purpose is to discuss whether this solution(separate LLM and VL) is acceptable , if accepted, I will continue to complete it.
ping @ywang96 @DarkLight1337

@jeejeelee
Init
6493ee4 
Signed-off-by: Jee Jee Li <[email protected]>
@jeejeelee jeejeelee marked this pull request as draft October 23, 2024 16:27
@github-actions GitHub Actions
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.

🚀

@jeejeelee jeejeelee marked this pull request as ready for review October 28, 2024 08:15
@jeejeelee
Delete redundant code
804a361 
Signed-off-by: Jee Jee Li <[email protected]>
@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Oct 29, 2024
DarkLight1337
DarkLight1337 approved these changes Oct 29, 2024
View reviewed changes
Copy link
Member

@DarkLight1337 DarkLight1337 left a comment

Choose a reason for hiding this comment

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

Looks good, sorry for making you wait!

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) October 29, 2024 02:33
@DarkLight1337 DarkLight1337 merged commit 7a4df5f into vllm-project:main Oct 29, 2024
76 checks passed
rasmith pushed a commit to rasmith/vllm that referenced this pull request Oct 30, 2024
@jeejeelee @rasmith
[Model][LoRA]LoRA support added for Qwen (vllm-project#9622)
91dfb3f 
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Randall Smith <[email protected]>
@DarkLight1337
Copy link
Member

DarkLight1337 commented Oct 31, 2024 •
edited
Loading

Just realized that the Supported Models page hasn't been updated yet. @jeejeelee can you open a new PR to update that page with the new LoRA support? We should also explicitly inherit from SupportsLoRA in QWenLMHeadModel.

@jeejeelee
Copy link
Collaborator Author

Just realized that the Supported Models page hasn't been updated yet. @jeejeelee can you open a new PR to update that page with the new LoRA support? We should also explicitly inherit from SupportsLoRA in QWenLMHeadModel.

Okay, handling it now

@jeejeelee
Copy link
Collaborator Author

We should also explicitly inherit from SupportsLoRA in QWenLMHeadModel.

Why do we need to do it?

@DarkLight1337
Copy link
Member

We should also explicitly inherit from SupportsLoRA in QWenLMHeadModel.

Why do we need to do it?

Easier to find which models support LoRA.

@jeejeelee
Copy link
Collaborator Author

We should also explicitly inherit from SupportsLoRA in QWenLMHeadModel.

Why do we need to do it?

Easier to find which models support LoRA.

Get it!

@jeejeelee jeejeelee deleted the qwen-support-lora branch October 31, 2024 05:44
This was referenced Nov 6, 2024
Open
Closed
Closed
Closed
JC1DA pushed a commit to JC1DA/vllm that referenced this pull request Nov 11, 2024
@jeejeelee @JC1DA
[Model][LoRA]LoRA support added for Qwen (vllm-project#9622)
35bbb1e 
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Loc Huynh <[email protected]>
sumitd2 pushed a commit to sumitd2/vllm that referenced this pull request Nov 14, 2024
@jeejeelee @sumitd2
[Model][LoRA]LoRA support added for Qwen (vllm-project#9622)
8486a62 
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Sumit Dubey <[email protected]>
sleepwalker2017 pushed a commit to sleepwalker2017/vllm that referenced this pull request Dec 13, 2024
@jeejeelee
[Model][LoRA]LoRA support added for Qwen (vllm-project#9622)
8a46649 
Signed-off-by: Jee Jee Li <[email protected]>
LeiWang1999 pushed a commit to LeiWang1999/vllm-bitblas that referenced this pull request Mar 26, 2025
@jeejeelee @LeiWang1999
[Model][LoRA]LoRA support added for Qwen (vllm-project#9622)
2541801 
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: LeiWang1999 <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@DarkLight1337 DarkLight1337 DarkLight1337 approved these changes

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.

[Feature]: LoRA support for Qwen model baichuan/qwen/chatlgm with lora adaption [feature]

2 participants

@jeejeelee @DarkLight1337