[Bug fix] Do not quantize weights Y when matmul X and Y both other ops outputs #43297
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! |
|
This change is aligned with python save_quant_model.py (save_quant_model.py could quantize Ernie3.0 but enable_mkldnn_int8 failed and this PR fixed it). Now Ernie3.0 enable_mkldnn_int8 could work successfully. |
lidanqing-intel
changed the title
lidanqing-intel
force-pushed
the
develop-fix-ernie3.0
branch
from
10bf1c2
to
6e72ec7
Compare
sfraczek
reviewed
Jun 8, 2022
|
@jczaja Hi could you please review this PR, we agreed to have at least two people to review the PR. |
|
你的PR已合入Paddle库，请关注后续测试结果。 |
lidanqing-intel
added a commit
that referenced
this pull request
Jun 21, 2022
…s outputs (#43297) * fix some matmul that X and Y both other ops outputs, do not dequantize the Y. * fix CI format * fix according to review
lidanqing-intel
added a commit
to lidanqing-intel/Paddle
that referenced
this pull request
Jun 22, 2022
…s outputs (PaddlePaddle#43297) * fix some matmul that X and Y both other ops outputs, do not dequantize the Y. * fix CI format * fix according to review
ZeyuChen
pushed a commit
that referenced
this pull request
Jun 23, 2022
* Correct elementwise quantization (#43693) * [Bug fix] Do not quantize weights Y when matmul X and Y both other ops outputs (#43297) * fix some matmul that X and Y both other ops outputs, do not dequantize the Y. * fix CI format * fix according to review Co-authored-by: joanna.wozna.intel <joanna.wozna@intel.com>
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Outdated suggestions cannot be applied.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
Bug fixes
PR changes
Others
Describe
Fix bug for ernie3.0 enable_mkldnn_int8, that do not quantize weights Y when matmul X and Y both other ops outputs