Skip to content

Conversation

@MatthewBonanni
Copy link

Enabling different hdim != hdim_v for hdim <= 64. This is required for MLA decode.

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
@MatthewBonanni MatthewBonanni marked this pull request as draft August 25, 2025 19:32
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
@MatthewBonanni MatthewBonanni marked this pull request as ready for review August 26, 2025 19:47
@LucasWilkinson LucasWilkinson merged commit ee4d25b into vllm-project:main Aug 26, 2025
1 check passed
@MatthewBonanni MatthewBonanni deleted the hdimdiff64 branch August 27, 2025 16:09
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.

2 participants