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

Guseul Heo et al. (2024)

Details and statistics

DOI: 10.1145/3620666.3651380

access: closed

type: Conference or Workshop Paper

metadata version: 2024-04-25

a service of  Schloss Dagstuhl - Leibniz Center for Informatics