Work

Fast On-device LLM Inference with NPUs

Year: 2024

Type: conference-paper

Abstract: ASLOLOS 25 Fast On-device LLM Inference with NPUs Artifact Evaluation

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.14392759

Author: Xu, Daliang

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W6968433301

FWCI:

Cites:

Cited by:

Related to: