1
LLM Serving and the Bus That Never Stops
深入剖析LLM服务中永不停止的“飞行中批处理”机制，解锁推理效率提升新思路
Article URL: https://joker666.github.io/blog/2026-06-02-llm-serving-in-flight-batching Comments URL: https://news.ycombinator.com/item?id=48414773 Poi…
2
Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling
创新异步代理框架巧妙平衡实时约束与长期推理需求，为动态调度难题提供有效解法。
arXiv:2605.29262v1 Announce Type: new Abstract: The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reac…