TensorRT-LLM icon indicating copy to clipboard operation
TensorRT-LLM copied to clipboard
verified publisher icon NVIDIA

enable medusa int8 weight only quantization

Open XiaobingSuper opened this issue 1 year ago • 2 comments

XiaobingSuper avatar May 16 '24 06:05 XiaobingSuper

@kaiyux, could you help review it?

XiaobingSuper avatar May 21 '24 01:05 XiaobingSuper

@XiaobingSuper Thanks for the support! We will review the changes in the internal codebase and get back to you.

kaiyux avatar May 21 '24 09:05 kaiyux

Hi @XiaobingSuper , we've merged your changes into main branch and thanks a lot for your contributing.

nv-guomingz avatar Jun 05 '24 09:06 nv-guomingz