SliceGPT: Compress Large Language Models by Deleting Rows and Columns Paper • 2401.15024 • Published Jan 26 • 69
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data Paper • 2401.10891 • Published Jan 19 • 59
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads Paper • 2401.10774 • Published Jan 19 • 54