Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training 事件

Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training arXiv:2605.26189v1 Announce Type: cross Abstract: Quantization-aware training (QAT) with low-bit floating-point formats enables efficient LLM deployment, yet introduces subtle failure modes invisible to standard training metrics. We present a systematic study of HiF8 W8A8 QAT for OpenPangu-Embedded-1B through the lens of Delayed Tensor Scaling (DTS). Across eight controlled experiments, we identify and disentang