fix_fused_rotary_position_embedding #74716
Merged
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
rotate_half为True时，正确的计算顺序如下：
而实际计算顺序是：
但是旧的单测，rotate_half为True时，前半部分的sin数据和后半部分的sin数据是一致的，此时s1和s0二者相等，所以跑出来的数据也相等了。
|
… fix_fused_rotary_position_embedding
… fix_fused_rotary_position_embedding
|
/re-run all-failed |
Luckycheng222
pushed a commit
to Luckycheng222/Paddle
that referenced
this pull request
Aug 25, 2025
* fix_fused_rotary_position_embedding * fix the ci test
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Outdated suggestions cannot be applied.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.
PR Category
Operator Mechanism
PR Types
Bug fixes
Description
fused_rotary_position_embedding API在use_neox_rotary_style为False时，反向传播计算逻辑存在错误。
Paddle 目前kernel中的反向计算逻辑
def paddle_backward_rotary_pos_emb(dL_dxprime, cos, sin):
return dL_dxprime * cos - rotate_half(dL_dxprime) * sin
正确的反向计算逻辑，可以和torch自动微分的结果对齐
def correct_backward_rotary_pos_emb(dL_dxprime, cos, sin):
return dL_dxprime * cos - rotate_half(dL_dxprime * sin)