[Feature]: Support hqq quantize method.
Minami-su opened this issue ยท 0 comments
Minami-su commented
๐ The feature, motivation and pitch
https://mobiusml.github.io/hqq_blog/
HQQ is a fast and accurate model quantizer that skips the need for calibration data. It's super simple to implement (just a few lines of code for the optimizer). It can crunch through quantizing the Llama2-70B model in only 4 minutes! ๐
Alternatives
No response
Additional context
No response