Add support for candle-flash-attn and candle-flash-attn-v3 in CUDA - #14
Merged
Merged
Conversation
alvarobartt
added this pull request to stack #15
September 25, 2026 07:48
This branch was successfully deployed
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR adds support for both
candle-flash-attnandcandle-flash-attn-v3in CUDA, but only for Ampere, Ada Lovelace and Hopper, meaning that both Turing and Blackwell as left aside. On Turing because the kernels require features such ascp.asyncor bfloat16 tensor cores, which are only in Ampere onward; and then for Blackwell the limitation is oncandlekernels which are missing coverage for sm100 and sm120 for the time being, so not discarding that support might come soon!