1
Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM Inference
边缘端智能压缩提示词，直击云LLM推理的语义损耗与成本痛点。
arXiv:2606.19364v1 Announce Type: new Abstract: The prefill stage of Large Language Model (LLM) inference is a growing contributor to cloud-scale ener…