GPTQ转化的INT8模型，如何运行呢？请大佬指教

IST-DASLab / gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

https://arxiv.org/abs/2210.17323

Apache License 2.0

1.81k stars 145 forks source link

Open xxm1668 opened 7 months ago