Compiler-Assisted Speculative Sampling for Accelerated LLM Inference on Heterogeneous Edge Devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mesa, Alejandro Ruiz y, Korol, Guilherme, Riesterer, Moritz, de Lima, João Paulo Cardoso, Castrillon, Jeronimo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.08060