trends.barnas.net

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

0219 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

KV cache reusecontinuous batchingdiffusion language model