CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights Paper • 2608.06763 • Published 6 days ago • 3
view article Article Open-source DeepResearch – Freeing our search agents +3 m-ric, albertvillanova, merve, thomwolf, clefourrier • Feb 4, 2025 • 1.32k