Giters

mit-han-lab / smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Home Page:https://arxiv.org/abs/2211.10438

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

SmoothQuant for llama

shhn1 opened this issue · comments

commented

Hi, authors!
Are you planning on supporting LLAMA in smoothquant？I am looking forward to the application of Smoothquant on LLAMA.

Thank you!

commented

Same here, when can you support LLAMA?

commented

I applied smoothquant in llama2, the ppl up to round 300 from 4.2 on SamSum dataset , I'm not sure whether the problem lies in the smoothquant method or in my own code。Would you mind have further discussion with email?