1
DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention
融合显著性token选择与部分注意力，加速扩散LLM推理，被ICML 2026接收，效率提升显著。
arXiv:2603.08026v2 Announce Type: replace-cross Abstract: Masked diffusion language models enable parallel token decoding, providing a promising alter…