AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference
Lee, Janghwan, Park, Jiwoong, Kim, Jinseok, Kim, Yongjik, Oh, Jungju, Oh, Jinwook, Choi, Jungwook
–arXiv.org Artificial Intelligence
Scaling Large Language Models (LLMs) with extended context lengths has increased the need for efficient low-bit quantization to manage their substantial computational demands. However, reducing precision to 4 bits frequently degrades performance due to activation outliers. To address this, we propose Asymmetric Microscaling 4-bit Floating-Point (AMXFP4) for efficient LLM inference. This novel data format leverages asymmetric shared scales to mitigate outliers while naturally capturing the asymmetry introduced by group-wise quantization. Unlike conventional 4-bit quantization methods that rely on data rotation and costly calibration, AMXFP4 uses asymmetric shared scales for direct 4-bit casting, achieving near-ideal quantization accuracy across various LLM tasks, including multi-turn conversations, long-context reasoning, and visual question answering. Our AMXFP4 format significantly outperforms MXFP4 and other leading quantization techniques, enabling robust, calibration-free 4-bit inference.
arXiv.org Artificial Intelligence
Nov-14-2024
- Country:
- Asia (1.00)
- Genre:
- Research Report > New Finding (0.67)
- Industry:
- Energy (0.68)
- Information Technology (0.46)
- Technology: