[XPU] support bf16 weight_scale in op weight_only_linear #73963
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! |
cqulilujia changed the title 
| /re-run all-failed |
cqulilujia force-pushed the weight_only_linear branch from b144150 to 5265396 Compare | /re-run all-failed |
| PADDLE_ENFORCE_XDNN_SUCCESS(r, "cast"); | ||
| } | ||
| const float* weight_scale_ptr = nullptr; | ||
| if (weight_scale.dims().size() != 0) { |
There was a problem hiding this comment.
为什么上面不需要考虑weight_scale.dims().size() != 0？这种情况调用cast会出错吗？
There was a problem hiding this comment.
考虑scalar tensor，dims().size()可能为0，但是numel为1，考虑是否是从numel来判断
There was a problem hiding this comment.
原有实现中dims().size()等于零时直接传nullptr进算子，所以不需要考虑scalar。cast出错风险我修一下
cqulilujia force-pushed the weight_only_linear branch from 5265396 to dcf0cd2 Compare | /re-run all-failed |
dynamicheart approved these changes Jul 16, 2025
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 Outdated suggestions cannot be applied.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
Custom Device
PR Types
New features
Description
Support fp16 weight_scale in op weight_only_linear for XPU