[XPU] add quantize_linear and dequantize_linear op #71375
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! |
Contributor
|
LGTM |
QingshuChen
approved these changes
Mar 6, 2025
YqGe585
pushed a commit
to YqGe585/Paddle
that referenced
this pull request
May 7, 2025
* [XPU] add quantize_linear and dequantize_linear op * update xhpc version
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Outdated suggestions cannot be applied.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
增加XPU下面的
quantize_linear以及dequantize_linear算子。受执行器的某些特殊限制，参考GPU和CPU的实现，增加了两个辅助的没有什么实际意义的算子。当前算子会忽略
qmin、bit_length等等参数。其原因有若干个，例如，python/paddle/nn/quant/format.py的调用入口只传了较少的参数，以及参考GPU和CPU的代码，中间若干层的调用中，会把这些参数逐渐都扔掉（即，不往下传）。此外，经过和业务方讨论，only_observer和round_type也只支持了默认值。此外，不支持
!is_test的情况，等以后有需求了再考虑补充。