Skip to content

[CB] Fixes for SDPA and CPU offloading#45733

Open
remi-or wants to merge 2 commits intomainfrom
cb-fix-k-race-bug
Open

[CB] Fixes for SDPA and CPU offloading#45733
remi-or wants to merge 2 commits intomainfrom
cb-fix-k-race-bug

Conversation

@remi-or
Copy link
Copy Markdown
Collaborator

@remi-or remi-or commented May 1, 2026

This PR fixes two issues:

  • SDPA attn used the wrong total_seqlen_k which led to crashes
  • CPU offloading did not copy the cache correctly when blocks were non-contiguous (fancy indexing)
    This PR fixes both issues.

@remi-or remi-or requested review from ArthurZucker and ydshieh May 1, 2026 03:59
@remi-or remi-or self-assigned this May 1, 2026
@HuggingFaceDocBuilderDev
Copy link
Copy Markdown

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

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