"NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing."

Guseul Heo et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.00579

access: open

type: Informal or Other Publication

metadata version: 2024-04-02

a service of  Schloss Dagstuhl - Leibniz Center for Informatics