Skip to content

CUDA: fix FlashAttention on Turing #13415

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

Conversation

JohannesGaessler
Copy link
Collaborator

Fixes #13306 (comment) .

The problem is that the V data is not being loaded correctly for nstages == 0 (no asynchronous data loading available) and I forgot to test this configuration prior to merging. Sorry!

@github-actions github-actions bot added Nvidia GPU Issues specific to Nvidia GPUs ggml changes relating to the ggml tensor library for machine learning labels May 9, 2025
@Dampfinchen
Copy link

Dampfinchen commented May 9, 2025

Nothing to apologize for, thanks for fixing it! :)

Fast fix, fast test - I can confirm it works again after this PR. Thanks for your great work!

@JohannesGaessler JohannesGaessler merged commit d891942 into ggml-org:master May 10, 2025
39 of 40 checks passed
Nexesenex added a commit to Nexesenex/croco.cpp that referenced this pull request May 14, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants