Skip to content

Conversation

@WoosukKwon
Copy link
Collaborator

The expert_ids tensor in fused_moe is a bit over-allocated. This PR fixes this for clarity.

Copy link
Collaborator

@pcmoritz pcmoritz left a comment

Choose a reason for hiding this comment

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

Nice fix!

@WoosukKwon WoosukKwon enabled auto-merge (squash) May 1, 2024 22:59
@WoosukKwon WoosukKwon merged commit 826b82a into main May 1, 2024
robertgshaw2-redhat pushed a commit to neuralmagic/nm-vllm that referenced this pull request May 6, 2024
z103cb pushed a commit to z103cb/opendatahub_vllm that referenced this pull request May 7, 2024
dtrifiro pushed a commit to opendatahub-io/vllm that referenced this pull request May 7, 2024
@WoosukKwon WoosukKwon deleted the minor-fix-moe branch May 13, 2024 17:47
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.

3 participants