Add ernie-3.0 mkldnn fp32 and int8 support #2468
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
lidanqing-intel
changed the title
|
Hi, @yeliang2258 please review and merge this PR. Now with this PR, both fp32 and int8 works, without using save_quant_model.py. Thanks. |
|
Paddle: Ernie-3.0 FP32 mkldnn, 1 thread on ICX is 65.45 QPS Ernie-3.0 INT8 mkldnn, 1 thread on ICX is 153.77 QPS |
lidanqing-intel
force-pushed
the
develop-ernie-3.0
branch
from
3650582 to
65a4fd4
Compare
|
Hi @ZeyuChen could you please merge this PR? @yeliang2258 has approved. |
|
@lidanqing-intel Thanks for your contributions! |
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Outdated suggestions cannot be applied.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
Others
Description
Add ernie-3.0 fp32 and int8 mkldnn support. The Paddle need to be after Ernie-3.0 int8 fix #43297 [Bug fix] Do not quantize weights Y when matmul X and Y both other ops outputs.