CUDA: fix Volta FlashAttention logic #11615
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
Nvidia GPU
|
I'm now getting this error: |
JohannesGaessler
force-pushed
the
cuda-fa-fix-logic
branch
from
ff0d3f6 to
5ee63ee
Compare
|
The code seems to have also been missing a return statement. |
Nexesenex
added a commit
to Nexesenex/croco.cpp
that referenced
this pull request
Feb 4, 2025
Author : Johannes Gaessler
tinglou
pushed a commit
to tinglou/llama.cpp
that referenced
this pull request
Feb 13, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #11583 (comment) .
The problem is that the kernel selection logic is wrong. The "tile" and "vec" kernels should be used when no tensor cores are available at all, not when the new tensor core type is unavailable.