Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled varianceby Alexander Stollenwerk, Laurent JacquesFirst…
Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacyby Feng Wang, M. Cenk Gursoy, Senem…
Post Training Quantization of Large Language Models with Microscaling Formatsby Sayeh Sharify, Utkarsh Saxena, Zifei…
Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantizationby Xinyuan Zhang, Jiang…
Characterizing the Accuracy – Efficiency Trade-off of Low-rank Decomposition in Language Modelsby Chakshu Moar, Faraz…
SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Modelsby Haojie Duanmu, Zhihang Yuan,…
LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkitby Ruihao Gong, Yang Yong,…
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networksby…
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Servingby Yujun Lin, Haotian Tang, Shang…
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantizationby…