SafeSpec论文提出动态反思采样，兼顾LLM解码速度与安全，为快速推理保驾护航
arXiv:2606.19755v1 Announce Type: cross Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safet…
基于扩散的LLM解码太慢？SAID用“脚手架感知”迭代策略，大幅提速且不损质量。
arXiv:2606.04974v1 Announce Type: new Abstract: Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising …
针对内存受限MoE大模型推理的优化方案，通过微调路由器实现专家重用，在Jetson Orin NX上获得1.77-1.99倍解码加速。
arXiv:2605.27081v1 Announce Type: cross Abstract: Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, r…