Fast Heterogeneous Serving: Scalable Mixed-Scale LLM Allocation for SLO-Constrained Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Jiaming, Nguyen, Duong Tung
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!