GPTQ introduced in: Frantar et al. 2022 — accurate post-training quantization for GPT models.
Object
Frantar et al. 2022 — accurate post-training quantization for GPT models
Primary source · preprint · 2022-10-31
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers — arXiv (Frantar, Ashkboos, Hoefler, Alistarh / IST Austria)