MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving
This work addresses a specific bottleneck in efficient LLM inference for deployment, offering an incremental improvement to existing microscaling formats.
The paper tackles the problem of outlier values degrading performance in ultra low-bit block floating-point formats for large language model serving, and proposes MX+, which repurposes the exponent field to increase outlier precision, achieving significantly higher model performance than 4-bit MX format with negligible overhead.
Reduced-precision data formats are crucial for cost-effective serving of large language models (LLMs). While numerous reduced-precision formats have been introduced thus far, they often require intrusive modifications to the software frameworks or are rather unconventional for widespread adoption across hardware vendors. In this paper, we instead focus on recent industry-driven variants of block floating-point (BFP) formats and conduct a comprehensive analysis to push their limits for efficient LLM serving. Our analysis shows that existing ultra low-bit BFP variants struggle to provide reasonable language model performance due to outlier values in blocks. To address the outliers with BFPs, we propose MX+, a cost-effective and non-intrusive extension designed for seamless integration into the microscaling (MX) formats. MX+ builds on the key insight that the outlier does not need to use its exponent field in the element data type, which allows us to repurpose the exponent field as an extended mantissa to increase the precision of the outlier element. Our evaluation shows that MX+ achieves significantly higher model performance compared to the 4-bit MX format (MXFP4) with negligible storage overhead and slowdown, thus offering a compelling alternative to MXFP4 or MXFP6 for efficient LLM inference.