if the whole block is excluded from the quantization, bug will occur

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

225 stars 19 forks source link

if the whole block is excluded from the quantization, bug will occur #141

Closed wenhuach21 closed 3 months ago

wenhuach21 commented 3 months ago

fixed