SOURCE-LINKED INTELLIGENCE

OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

NVFP4 is an efficient microscaling format for low-bit inference, but activation outliers can still degrade quantization accuracy within NVFP4 blocks. Within each quantization block, large activations can dominate the block scale, increasing the quantization error of the remaining values sharing the same scale. Existing post-training quantization (PTQ) methods mitigate outlier errors through strategies such as mixed precision, rotation, or residual compensation, but these approaches are either not specifically tailored to NVFP4 or introduce additional computation. In this work, we revisit NVFP4

Read original source ↗ Open in workspace

recordType

paper

region

Global