Add quantized mixtral support #2673
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
simon-mo
reviewed
Jan 30, 2024
AlpinDale
reviewed
Jan 30, 2024
| @@ -0,0 +1,412 @@ | |||
| # coding=utf-8 | |||
There was a problem hiding this comment.
Instead of inserting a new file just for this, would it be better to add the MLP class again in mixtral.py and falling back to the original code for instances where linear method is None?
There was a problem hiding this comment.
Hi @AlpinDale, thank you for the comment. We are doing this to resolve release blocker. What you mentioned will be the right fix for the future.
simon-mo
approved these changes
Jan 31, 2024
NikolaBorisov
pushed a commit
to deepinfra/vllm
that referenced
this pull request
Jan 31, 2024
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
alexm-redhat
pushed a commit
to neuralmagic/nm-vllm
that referenced
this pull request
Feb 13, 2024
1 task
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is a hacky way to add back the quantization support for Mixtral, which was broken by the optimization in #2542 . NOTE: This is a temporary hack and we need to fix this in the future.