ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16 Text Generation โข Updated Sep 17, 2024 โข 46 โข 46
FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design Paper โข 2401.14112 โข Published Jan 25, 2024 โข 21