117 citations · 133 across the 4 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.AR2024★ 117 cited
NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing
Guseul Heo, Sangyeop Lee, Jaehong Cho +6
Modern transformer-based Large Language Models (LLMs) are constructed with a series of decoder blocks. Each block comprises three key components: (1) QKV generation, (2) multi-head…
cs.LG2024★ 10 cited
Accelerating String-Key Learned Index Structures via Memoization-based Incremental Training
Minsu Kim, Jinwoo Hwang, Guseul Heo +3
Learned indexes use machine learning models to learn the mappings between keys and their corresponding positions in key-value indexes. These indexes use the mapping information as…