neural-compressor
neural-compressor copied to clipboard
Smoothquant refactor for 3.x API
Type of Change
Smoothquant refactor for 3.x API API changed
Description
- [x] refactor new API - prepare/convert
- [ ] add ut for new API, remove unnecessary old ones
- [x] fix eager model/prepared model issue for old quantize API
- [ ] support calib_fun rather than dataloader for auto-tuning
- [ ] add ut for auto-tuning
- [ ] modify 3.x sq example
Expected Behavior & Potential Risk
ut pass