method · first seen 10 Oct 2026
LLM serving scheduling
Also: LLM request scheduling, request scheduling for LLM serving
Policies for routing and batching LLM inference requests across distributed GPU instances.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Vesta: Queueing-Aware LLM Scheduling for Real-World WorkloadsPapers · 10 Oct 2026 · Lancheng Zou, Bowen Li, Wei Mao, Wenbin Ye, Lecheng Li, Kai Liu, Chao Deng, Jian…
- Lightweight Scheduling Policies for Continuously Batched LLM Serving Across GPU ArchitecturesPapers · 11 Oct 2026 · Ashman Mehra, Akshan Agrawal, Aryeh Carmi
- DWISE: Denoising Workload-Informed Scheduling EnginePapers · 29 Oct 2026 · Lie Li, Wen Li, Junxiao Shen, Jindong Gu, Guosheng Hu
- Fairway: Load-Aware KV Cache Reuse for LLM Prefill SchedulingPapers · 1 Nov 2026 · Hamidreza Alikhani, Nazmul Takbir, Matin Khajavi, Rajat Bhattacharjya, Sangeetha…
Latest sources
- Fairway: Load-Aware KV Cache Reuse for LLM Prefill SchedulingPapers · 1 Nov 2026 · Hamidreza Alikhani, Nazmul Takbir, Matin Khajavi, Rajat Bhattacharjya, Sangeetha…
- DWISE: Denoising Workload-Informed Scheduling EnginePapers · 29 Oct 2026 · Lie Li, Wen Li, Junxiao Shen, Jindong Gu, Guosheng Hu
- Lightweight Scheduling Policies for Continuously Batched LLM Serving Across GPU ArchitecturesPapers · 11 Oct 2026 · Ashman Mehra, Akshan Agrawal, Aryeh Carmi
- Vesta: Queueing-Aware LLM Scheduling for Real-World WorkloadsPapers · 10 Oct 2026 · Lancheng Zou, Bowen Li, Wei Mao, Wenbin Ye, Lecheng Li, Kai Liu, Chao Deng, Jian…