Código QR (código de barras bidimensional)

Formal schedulability analysis for LLM inference: TTFT and TBT deadline guarantees via response-time theory

IntroductionLarge language model (LLM) inference systems operate under strict latency service-level objectives (SLOs): a deadline on the first output token (TTFT) and a maximum inter-token interval (TBT). Real-time (RT) scheduling theory provides formal schedulability tests, worst-case response-time...

Fuld beskrivelse

Na minha lista:
Principais autores: Amine Marref, Khaled Tarmissi, Hassene Chaibi
Format: Artigo
Sprog:Inglês
Udgivet: Frontiers Media S.A. 2026-06-01
Serier:Frontiers in Computer Science
Fag:
admission control
LLM inference
real-time scheduling
schedulability analysis
service-level objectives
TBT
Online adgang:https://www.frontiersin.org/articles/10.3389/fcomp.2026.1873627/full
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

Lignende værker