Work

Code Artifact for Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking

Year: 2024

Type: preprint

Abstract: Code for the paper "Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking".

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2412.01380

Authors: Federici, Marco, Belli, Davide, van Baalen, Mart, Jalalirad, Amir, Skliar, Andrii, Major, Bence, Nagel, Markus, Whatmough, Paul

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4405034086

Cites:

Cited by:

Related to: 10