-
Notifications
You must be signed in to change notification settings - Fork 4.3k
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
Fix LoRA Fuse/Unfuse in Hybrid Engine #3563
Fix LoRA Fuse/Unfuse in Hybrid Engine #3563
Conversation
@microsoft-github-policy-service agree |
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.
This looks great! Thank you!
@sxjscience - Thank you so much for this detailed PR and investigation! Sorry for the delay in reviewing! |
@sxjscience - I have put this PR to auto-merge when the tests pass but I see that the latest round of tests has one failing nv-inference test. Can you please take a look and resolve the issue? |
Will take a look later today. |
Head branch was pushed to by a user without write access
@awan-10 Would you have time to take a look at the latest change? CI has been fixed. |
fuse_lora
andunfuse_lora
in InferenceContainers. It should fix [BUG]RuntimeError: The size of tensor a (6144) must match the size of tensor b (8192) at non-singleton dimension 0 #3543set_q_k_v
in GPTNeo