chengtao-lv

https://scholar.google.com/citations?user=r8vseSUAAAAJ&hl=en [email protected]

SenseTime Research Incoming Ph.D. @ NTU # Efficient AI

Results 1 comments of


                                            chengtao-lv

fail to start awq quantized model with lightllm on qwen2-7b-instruct

Hi, granularity is not per_channel. You should adjust to **per_group**.