trends.barnas.net

method · first seen 13 Oct 2026

token-level scheduling

Admitting and pacing requests at per-token granularity to control inter-token latency during LLM decoding.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

serverless inferencechunked prefill