华为昇腾NPU上实现免训练4-bit FlashAttention，大幅降低LLM推理内存与计算开销。
arXiv:2607.04302v1 Announce Type: cross Abstract: We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAtten…
新方法MosaicQuant通过分离内点与外点实现统一4-bit大模型量化，提升精度与效率。
arXiv:2606.15652v1 Announce Type: new Abstract: 4-bit quantization significantly reduces the memory footprint and accelerates the inference of large l…
针对全模态大语言模型4比特量化时模态分布异质难题，MorphoQuant提出模态感知量化框架，有效压缩模型同时保持性能。
arXiv:2606.04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language …