Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving

8 December 2023

Papers citing "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving"

2 / 2 papers shown

Title
Legilimens: Performant Video Analytics on the System-on-Chip Edge M. Ramanujam Yinwei Dai Kyle Jamieson Ravi Netravali 71 0 0 29 Apr 2025
EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism Yanxi Chen Xuchen Pan Yaliang Li Bolin Ding Jingren Zhou LRM 21 31 0 08 Dec 2023