-
Notifications
You must be signed in to change notification settings - Fork 3.7k
Update vllm to 0.6.3 #1711
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
Update vllm to 0.6.3 #1711
Conversation
|
@merrymercy @Ying1123 @zhyncs The PR tests passed. Pls help review for some patched code. It's better to trigger the nightly eval for more compatibility tests. |
| ) | ||
|
|
||
| # workaround | ||
| from vllm.model_executor.layers.linear import LinearBase |
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.
do we fully re-sync this file?
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.
No, I just updated the part which is not compatible. Do we need to fully sync it?
Co-authored-by: Ke Bao <[email protected]>
|
Nightly eval passed. |
Co-authored-by: Ke Bao <[email protected]>
Motivation
To support Qwen2-VL in #1546, there some dependencies need to be upgraded.