[Accuracy diff No.96] Fix accuracy diff for paddle.incubate.nn.functional.variable_length_memory_efficient_attention API #498
Conversation
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
|
Thanks for your contribution! |
Collaborator
|
done in #540 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
修复
variable_length_memory_efficient_attentionAPI 的两处地方。Paddle 中该 API 的实现是调用 cutlass 的，所以认为它的实现正确，以修改 PaddleAPITest 框架为主。tester/api_config/config_analyzer.py：mask数组中的元素要么是 -inf 要么是 0，在计算时 attention 的结果加上 mask 再执行 softmax 即可完成 mask 掉某些元素的效果。tester/paddle_to_torch/rules.py：修复了 K 和 V 扩展 head_dim 的方法；修复了 mask 和 mask_fill 顺序，前者应该在前否则它会覆盖掉 mask_fill 的结果