精度损失很多
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
### Motivation
为啥我采用 训练后量化精度下降的点数比较多
另外，只能节省现存，吞吐提高不明显，在A100 测试的结果
### Related resources
_No response_
### Additional context
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.