[New features] Support FlashMask with 512/512 and 576/512 head dimensions - #1724
Merged
Conversation
risemeup1111
suggested changes
Aug 12, 2026
Contributor
There was a problem hiding this comment.
| 序号 | 位置 | 优先级 | 状态 |
|---|---|---|---|
| 1 | FA4 大维度缺少前后向回归 |  |
❌ |
固定的 flash-attention 后端已支持 512/512 和 576/512，原先的 FA2 回退问题已修复；当前仍缺少这两个组合的 SM100 FlashMask 前向、反向回归测试。
Powered by Nyanpasu with gpt-5.5 xhigh, please check the suggestions carefully.
baoqiwen
changed the title
Contributor
|
@risemeup1111 review这段代码 |
risemeup1111
suggested changes
Aug 13, 2026
risemeup1111
left a comment
risemeup1111
left a comment
Contributor
There was a problem hiding this comment.
后端同步已解决 FA4 dispatch 问题，但新增的 512/512、576/512 组合仍没有 SM100 FlashMask 前向、反向回归测试，原 P1 判定为部分修复。
Powered by Nyanpasu with gpt-5.5 xhigh, please check the suggestions carefully.
Contributor
|
@risemeup1111 再次review |
Contributor
|
已完成复核。当前 HEAD 与上一轮相同：FA4 后端已支持 512/512、576/512，但仍没有这两个组合的 SM100 FlashMask 前向、反向回归测试，因此 P1 仍保留，当前评审结论仍为需要修改。请补充代表性用例后再复核。 |
Collaborator
Author
|
本地测试已通过 |
sneaxiy
approved these changes
Aug 13, 2026
risemeup1
approved these changes
Aug 13, 2026
Contributor
|
✅ Cherry-pick successful! Created PR: #1736 |
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
5 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Category
Operator Mechanism
PR Types
New features
Description
开启 paddlefleet flashmask d512/dv512 d576/dv512 的支持
是否引起精度变化
否