Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference

Junyi Luo, Xinting Jiang, Tai-Hao Wen +9

Microscaling (MX) is now the standard for low-bit large language model (LLM) inference. Its 4-bit form MXFP4 still loses substantial accuracy, because existing MX formats fix eithe…