Skip to content

Fix qvm_split_k incorrect batch stride calculation#3497

Open
angeloskath wants to merge 2 commits intomainfrom
qvm-split-k
Open

Fix qvm_split_k incorrect batch stride calculation#3497
angeloskath wants to merge 2 commits intomainfrom
qvm-split-k

Conversation

@angeloskath
Copy link
Copy Markdown
Member

Fixes #3480 .

Copy link
Copy Markdown
Collaborator

@zcbenz zcbenz left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] quantized_matmul produces wrong results for GQA expand_dims broadcasting when M < vector_limit

2 participants