Conference

DynaSplit: Latency-Aware Dynamic Model Partitioning for Large Language Model Inference in the Edge-Cloud Continuum

Bibliographic Details
Title: DynaSplit: Latency-Aware Dynamic Model Partitioning for Large Language Model Inference in the Edge-Cloud Continuum
Authors: Patel, Tejas Pravinbhai, Shivam, Sandeep, Padhy, Amit Kumar, Vulugunda, Bharadwaj, Kulkarni, Chaitanya, Medicherla, Chandrashekhar
Source: 2026 World Conference on Computational Science and Technology (WcCST) Computational Science and Technology (WcCST), 2026 World Conference on. :364-369 Mar, 2026
Relation: 2026 World Conference on Computational Science and Technology (WcCST)
Database: IEEE Xplore Digital Library
Description
ISBN:9798331599669
9798331599676
DOI:10.1109/WcCST67302.2026.11496291