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

Qbits related log #151

Closed zhewang1-intc closed 1 month ago

zhewang1-intc commented 1 month ago

as title, for better user experience.

zhewang1-intc commented 1 month ago

@wenhuach21 could u pls take a look?