Add int8 support for matmul+elementwise_add fuse pass #45077
Merged
Conversation
This file contains 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! |
wozna
added
Intel
int8
and removed
contributor
tsocha
reviewed
Aug 11, 2022
There was a problem hiding this comment.
I can see that in many places there is if(residual) maybe it is worth to break this pass into normal version and residual version?
If it will be done properly it should reduce risk of bugs in the future development. Readability of the code can be higher as well.
python/paddle/fluid/contrib/slim/quantization/quant2_int8_mkldnn_pass.py
Outdated
Show resolved
Hide resolved
Silv3S
approved these changes
Aug 22, 2022
|
@jiangjiajun Please start your review |
|
你的PR已合入Paddle库，请关注后续测试结果。 |
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Outdated suggestions cannot be applied.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 types
Performance optimization
PR changes
OPs
Describe
This PR add int8 support for
matmul_elementwise_add_mkldnn_fuse_pass.Moreover I unified the order of passes in quantization with and without serialization, following the order of passes for use_mkldnn.