Compute-efficient-inference - a dwidlee Collection

dwidlee 's Collections

Compute-efficient-inference

Compute-efficient-inference

updated Feb 22

FlashDecoding++: Faster Large Language Model Inference on GPUs

Paper • 2311.01282 • Published Nov 2, 2023 • 35
Exponentially Faster Language Modelling

Paper • 2311.10770 • Published Nov 15, 2023 • 118
Neural Network Diffusion

Paper • 2402.13144 • Published Feb 20 • 94