PaddleNLP
PaddleNLP copied to clipboard
FP8 PTQ With Physical Dependency 0515
PR types
New features
PR changes
APIs
Description
PaddleNLP设计逻辑: llm/fp8quant.py 定义FP8的量化逻辑,将FP8UniformObserver写入QuantConfig中 llm/fp8finetune_generation.py 调用llm/fp8quant.py中的量化逻辑,完成全部量化过程
Thanks for your contribution!
Codecov Report
All modified and coverable lines are covered by tests :white_check_mark:
Project coverage is 55.42%. Comparing base (
5da340e
) to head (8ff1f64
). Report is 663 commits behind head on develop.
:x: Your project check has failed because the head coverage (55.42%) is below the target coverage (58.00%). You can increase the head coverage or adjust the target coverage.
Additional details and impacted files
@@ Coverage Diff @@
## develop #8443 +/- ##
========================================
Coverage 55.42% 55.42%
========================================
Files 617 617
Lines 96281 96281
========================================
Hits 53366 53366
Misses 42915 42915
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
This Pull Request is stale because it has been open for 60 days with no activity. 当前Pull Request 60天内无活动,被标记为stale。
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.
This Pull Request is stale because it has been open for 60 days with no activity. 当前Pull Request 60天内无活动,被标记为stale。
This Pull Request is stale because it has been open for 60 days with no activity. 当前Pull Request 60天内无活动,被标记为stale。