Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
New SOTA 4-bit weight and KV quantization with optimized GPU performance (arxiv.org)
3 points by Hugsun on May 14, 2024 | hide | past | favorite



Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: