AFPQ: Asymmetric Floating Point Quantization for LLMs

3 November 2023

Papers citing "AFPQ: Asymmetric Floating Point Quantization for LLMs"

3 / 3 papers shown

Title
AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference Janghwan Lee Jiwoong Park Jinseok Kim Yongjik Kim Jungju Oh Jinwook Oh Jungwook Choi 44 2 0 15 Nov 2024
Scaling Laws for Mixed quantization in Large Language Models Zeyu Cao Cheng Zhang Pedro Gimenes Jianqiao Lu Jianyi Cheng Yiren Zhao MQ 33 1 0 09 Oct 2024
HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization Wenxuan Liu Saiqian Zhang MQ 37 5 0 30 May 2024