Skip to content
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

Fix FlashAttention debug test, FP32 assert #7684

Merged

Conversation

JohannesGaessler
Copy link
Collaborator

Fixup to #7527 (comment) .

Removes an incorrect assert for FP32 Flashattention. Pads the number of elements for per KV cache row in the tests to a multiple of the block size. The backend is still going to return that the head size is not supported but I think that if something like this were to ever be implemented padding would be the only sensible way to do it.

@github-actions github-actions bot added testing Everything test related Nvidia GPU Issues specific to Nvidia GPUs ggml changes relating to the ggml tensor library for machine learning labels Jun 1, 2024
@JohannesGaessler JohannesGaessler merged commit e141ce6 into ggerganov:master Jun 1, 2024
67 checks passed
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 testing Everything test related
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants