熵-时间推断：超越注意力的自组织大语言模型解码
Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
AI总结：
本文提出熵-时间推断方法，通过自组织架构实现基于熵的解码优化，提升大语言模型推理效率与稳定性。
摘要：
现代大语言模型（LLM）推理引擎在固定解码规则下优化吞吐量和延迟，将生成视为时间上的线性进程。我们提出了一种根本不同的范式：熵-时间推断，其中解码由不确定性流动而非token索引驱动。我们引入了一种自组织推理架构，将调度、注意力稀疏化和采样温度在统一的熵控制目标下联合耦合。我们的方法扩展了vLLM，通过熵感知调度、熵导向的分页注意力块修剪以及自适应温度控制，在目标熵范围内稳定生成。这将推理转化为一种资源智能的热力学过程，将计算分配到最大化不确定性减少的地方。我们展示了具体系统设计、伪代码和集成计划，证明熵可以作为可扩展LLM推理的首要控制信号。
英文摘要：
Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time inference, where decoding is governed by the flow of uncertainty rather than token index. We introduce a self\-organizing inference architecture that jointly couples scheduling, attention sparsification, and sampling temperature under a unified entropy control objective. Our method extends vLLM with entropy-aware scheduling, entropic pruning of paged attention blocks, and adaptive temperature control that stabilizes generation near a target entropy regime. This transforms inference into a resource\-intelligent thermodynamic process that allocates computation where uncertainty reduction is maximized. We present a concrete systems design, pseudocode, and integration plan, demonstrating how entropy can serve as a first\-class control signal for scalable LLM inference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
