Jungi Lee, Junyong Park 0005, Soohyun Cha, JaeHoon Cho, Jaewoong Sim. MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving. In Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture, MICRO 2025, Seoul, Republic of Korea, October 18-22, 2025. pages 869-883, ACM, 2025. [doi]
Abstract is missing.