04:00
2026-05-27
arxiv.org
machine-learning
Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training
Researchers at OpenPangu identified two failure modes in HiF8 W8A8 quantization-aware training for the OpenPangu-Embedded-1B model: amax saturation, which corrupts knowledge-sensitive representations …