LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Gridby Tianyi Zhang, Anshumali ShrivastavaFirst…
BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networksby Jacob Nielsen, Peter Schneider-KampFirst submitted to…
On Exact Bit-level Reversible Transformers Without Changing Architecturesby Guoqiang Zhang, J.P. Lewis, W. B. KleijnFirst…
Accuracy is Not All You Needby Abhinav Dutta, Sanjeev Krishnan, Nipun Kwatra, Ramachandran RamjeeFirst submitted…
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisionby Jay Shah, Ganesh Bikshandi, Ying Zhang,…
Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computingby Cui…
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradientsby Zhenyu Zhang, Ajay Jaiswal, Lu…
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantizationby Xijie Huang, Zechun Liu, Shih-Yang Liu,…
Balance of Number of Embedding and their Dimensions in Vector Quantizationby Hang Chen, Sankepally Sainath…
Quantizing YOLOv7: A Comprehensive Studyby Mohammadamin Baghbanbashi, Mohsen Raji, Behnam GhavamiFirst submitted to arxiv on:…