LeanModels/DFloat11 · AI Repo StatsLELeanModels/DFloat11
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
LLM & mô hình nền tảngPython Apache-2.0 40tạo 2025-04-15 #compression#diffusion-models#gpu#llm#lossless-compression-algorithm