1
Enabling KV Caching of Shared Prefix for Diffusion Language Models
扩散语言模型推理加速新方案，通过共享前缀KV缓存显著提升效率，结构简洁效果亮眼。
arXiv:2606.07571v1 Announce Type: new Abstract: Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM)…