activity
20232025
most citedPriority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference

2 citations · 4 across the 8 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

CASTILLO: Characterizing Response Length Distributions of Large Language Models

Daniel F. Perez-Ramirez, Dejan Kostic, Magnus Boman

Efficiently managing compute resources for Large Language Model (LLM) inference remains challenging due to the inherently stochastic and variable lengths of autoregressive text gen…