-
-
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
[Model][LoRA]LoRA support added for Qwen #9622
Conversation
Signed-off-by: Jee Jee Li <[email protected]>
👋 Hi! Thank you for contributing to the vLLM project. 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:
🚀 |
Signed-off-by: Jee Jee Li <[email protected]>
ccc2f34
to
6462961
Compare
Signed-off-by: Jee Jee Li <[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.
Looks good, sorry for making you wait!
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: Randall Smith <[email protected]>
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 |
Okay, handling it now |
Why do we need to do it? |
Easier to find which models support LoRA. |
Get it! |
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: NickLucche <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: NickLucche <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: Linkun Chen <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: Loc Huynh <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: Sumit Dubey <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: Maxime Fournioux <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]> Signed-off-by: Tyler Michael Smith <[email protected]>
Signed-off-by: Jee Jee Li <[email protected]>
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