MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving
Open Access
- 17 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 869-883
Abstract
No abstract availableAll Related Versions
Funding Information
- DOE Office of Science (DE-SC0024079)
This publication has 33 references indexed in Scilit:
- Intel Gaudi 3 AI Accelerator: Architected for Gen AI Training and Inference2024
- Cambricon-Q: A Hybrid Architecture for Efficient Training2021
- RaPiD: AI Accelerator for Ultra-low Precision Training and Inference2021
- DRQ: Dynamic Region-based Quantization for Deep Neural Network Acceleration2020
- Accel-Sim: An Extensible Simulation Framework for Validated GPU Modeling2020
- SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training2020
- A Configurable Cloud-Scale DNN Processor for Real-Time AI2018
- Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation2018
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015