Mengzhao Chen

PrefixQuant. An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization

CF-ViT. (AAAI 2023 Oral) Pytorch implementation of "CF-ViT: A General Coarse-to-Fine Method for Vision Transformer"

INT_vs_FP. [ICML 2026]A framework to compare low-bit integer and float-point formats

SMMix. [ICCV 23]This is a Pytorch implementation of our paper "SMMix: Self-Motivated Image Mixing for Vision Transformers"

chenmnz.github.io. HTML

AutoGPTQ-bugfix. An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.