Fix for breaking changes in xformers 0.0.21 #834
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
WoosukKwon
changed the title
zhuohan123
approved these changes
Aug 23, 2023
| self.num_heads, | ||
| padded_len, | ||
| prompt_len, |
There was a problem hiding this comment.
What is the reason for the change from padded_len to prompt_len here?
This was
linked to
issues
Aug 23, 2023
This was referenced Aug 23, 2023
randxie
pushed a commit
to randxie/vllm
that referenced
this pull request
Aug 29, 2023
liuyanyi
pushed a commit
to liuyanyi/vllm
that referenced
this pull request
Sep 12, 2023
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
4 tasks
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Outdated suggestions cannot be applied.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.
Fixes #832
This PR fixes the breaking changes made in the latest release of xformers. Specifically, now the xformers attention bias should have the batch dimension, which is 1 in the current vLLM implementation.