arXiv Computation and Language By Hao Yu, Zheng Li, Dayiheng Liu, Jianwei Zhang

H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference

Read the original on arXiv Computation and Language →

The paper introduces H-Scale, a lightweight post-processing technique for refining per-group scaling factors in NVFP4 quantized large language models. By using a diagonal second-order proxy from calibration activations, H-Scale selects hardware-valid scales that directly target layer output perturbation rather than just weight reconstruction error. Experiments on mainstream LLMs show that H-Scale improves NVFP4 baselines and brings several variants closer to BF16 performance without adding inference overhead.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning
Sep 3

UE5M3 FP4 Block Scaling for Stable Language Model Pretraining

The paper introduces a new 4‑bit floating‑point (FP4) pretraining approach that pairs E2M1 payloads with unsigned E5M3 block scales, enabling periodic tensor scaling and selective stochastic rounding while eliminating the randomized Hadamard transform. Using this method, the authors pretrained a Nemotron‑H 8B model on nearly 190 billion tokens, achieving lower training and validation losses compared to NVIDIA’s Transformer Engine. The approach also improves inference performance and demonstrates a 21.2 % increase in token throughput when certain optimizations are removed.

By Robert Hu, Carlo Luschi, Paul Balanca