↓Skip to main content

🏢 University at Albany, SUNY

MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
·1848 words·9 mins· loading · loading
AI Generated Natural Language Processing Large Language Models 🏢 University at Albany, SUNY
MagR: a novel preprocessing technique boosts post-training quantization of LLMs by reducing weight magnitudes without inference overhead, achieving state-of-the-art performance.
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
·2398 words·12 mins· loading · loading
Natural Language Processing Large Language Models 🏢 University at Albany, SUNY
CoMERA achieves 2-3x faster AI model training via rank-adaptive tensor optimization, significantly improving both computing and memory efficiency.