search

intel / auto-round

Advanced Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"
https://arxiv.org/abs/2309.05516
Apache License 2.0
132 stars 18 forks source link

refine the code #143

Closed wenhuach21 closed 1 month ago

wenhuach21 commented 1 month ago

1 refine the code structure 2 improve the readability of the minmax tuning space 3 fix some bugs