Add moe_combine_no_weight op #73531
Merged
Add moe_combine_no_weight op #73531
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! |
lshpku force-pushed the moe-combine-no-weight branch 2 times, most recently from 1d3e4ca to a28c362 Compare lshpku force-pushed the moe-combine-no-weight branch from a28c362 to 2ba7ae4 Compare lshpku force-pushed the moe-combine-no-weight branch from 27e782f to cd57c5d Compare lshpku force-pushed the moe-combine-no-weight branch from cd57c5d to ed8bb03 Compare 
zhangbo9674 approved these changes Jun 23, 2025
zyfncg reviewed Jun 23, 2025
| const MetaTensor& scatter_index, | ||
| MetaTensor* y); | ||
| | ||
| void MoeCombineNoWeightInferMeta(const MetaTensor& x, |
There was a problem hiding this comment.
这个算子之后会按API正确性的要求重写，我看了下它现在不支持大Tensor也不支持0-Size，这次算子迁移的任务太匆忙，只有半天时间，我也没来得及检查
zyfncg approved these changes Jun 23, 2025
lshpku added a commit to lshpku/Paddle that referenced this pull request Jun 23, 2025
This reverts commit 53919d3.
From00 pushed a commit to From00/Paddle that referenced this pull request Jun 24, 2025
* Add moe_combine_no_weight op * Remove seqlen and k from parameters * Set no_need_buffer for x
swgu98 pushed a commit that referenced this pull request Jun 24, 2025
* Add moe_combine_no_weight op (#73531) * Add moe_combine_no_weight op * Remove seqlen and k from parameters * Set no_need_buffer for x * Add moe_combine_no_weight Op * Update --------- Co-authored-by: Shuhao Liang <50269654+lshpku@users.noreply.github.com>
From00 added a commit to From00/Paddle that referenced this pull request Jun 24, 2025
* Add moe_combine_no_weight op (PaddlePaddle#73531) * Add moe_combine_no_weight op * Remove seqlen and k from parameters * Set no_need_buffer for x * Add moe_combine_no_weight Op * Update --------- Co-authored-by: Shuhao Liang <50269654+lshpku@users.noreply.github.com>
XiaoguangHu01 pushed a commit that referenced this pull request Jun 25, 2025
* Add moe_combine_no_weight OP (#73592) * Add moe_combine_no_weight op (#73531) * Add moe_combine_no_weight op * Remove seqlen and k from parameters * Set no_need_buffer for x * Add moe_combine_no_weight Op * Update --------- Co-authored-by: Shuhao Liang <50269654+lshpku@users.noreply.github.com> * Empty-Commit --------- Co-authored-by: Shuhao Liang <50269654+lshpku@users.noreply.github.com>
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
New features
Description
新增
paddle.incubate.nn.functional.moe_combine_no_weightop及其反向Pcard-85711