Skip to content

Optimize FlashMask v3, which is ~20% slower than FA3 Varlen.#116

Open
baoqiwen wants to merge 1 commit intoPaddlePaddle:mainfrom
baoqiwen:bqw_fa3_prof
Open

Optimize FlashMask v3, which is ~20% slower than FA3 Varlen.#116
baoqiwen wants to merge 1 commit intoPaddlePaddle:mainfrom
baoqiwen:bqw_fa3_prof

Conversation

@baoqiwen
Copy link
Copy Markdown

No description provided.

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.

1 participant