QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khanna, Danush, Guru, Aditya Kumar, Sridhar, Srivarshinee, Ahmed, Zidan, Bahirwani, Rubhav, Malhotra, Meetu, Jain, Vinija, Chadha, Aman, Das, Amitava, Ghosh, Kripabandhu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence I.2.0; I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.22396