Optimize and extend moe_permute & unpermute op, with docfix. #73564
+213 −108
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! |
| /re-run all-failed |
1 similar comment
| /re-run all-failed |
lshpku approved these changes Jun 26, 2025
zyfncg approved these changes Jun 26, 2025
| Shape: [seqlen_broadcasted, 1], dtype: float32. | ||
| - scale_unzipped: Scaled tensor (only valid when hidden_states is fp8). | ||
| Shape: [seqlen_broadcasted, (token_len + 127) // 128], dtype: float32. | ||
There was a problem hiding this comment.
后续我会单独补充example，感谢建议
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
4 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 Outdated suggestions cannot be applied.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
Improvements
Description
Optimize and extend moe_permute & unpermute op, with docfix.
pcard-91067