1
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
提出状态-时间一致后训练量化方案，突破扩散大语言模型部署瓶颈，降低模型推理成本。
arXiv:2606.04945v1 Announce Type: new Abstract: Diffusion large language models (DLLMs) have recently emerged as a promising alternative to autoregres…