Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

2026-05-26 · Zhanfeng Feng, Shuai Guo, Xin Di, Long Peng, Yang Cao, Zhengjun Zha arxiv

This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public ViDiT-Q post-training quantization pipeline to Wan2.2 under the HiFloat4 numerical format. We quantize the main linear layers in both Wan2.2 transformer modules with W4A4 HiFloat4 fake quantization, keep numerically sensitive boundary modules in high precision, and introduce an activation-tail-aware percentile calibration module for channel-mask construction. Together with compact PTQ-state restoration, this design reduces the influence of rare calibration outliers while keeping the runtime HiFloat4 arithmetic and sampling pipeline unchanged.

📄 PDF Abstract BibTeX arXiv:2605.26628

Code (0)

등록된 구현이 없습니다.

Tasks

Text-to-Video Generation

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats

2026-02-13 · Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao 외 arxiv

As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family of formats tailored for Ascend NPUs. Thr…

Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion Transformers

2026-05-31 · Yiming Zhao arxiv

We present a post-training quantization (PTQ) approach for Wan2.1-T2V-14B, a 14-billion-parameter text-to-video diffusion transformer, targeting the W8A8 HiFloat8 (HiF8) format on Ascend 910B NPUs. A central challenge in…

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

2026-07-29 · Hei Yi Mak, Shadan Golestan, Hoang Le, Mehran Taghian Jazi 외 arxiv

We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveal…

Reinforcement Learning

W4A4 Quantization for Inference on Wan2.2-I2V-A14B

2026-06-28 · Yidong Chen, Chengyu Shi, Jiahao Liu arxiv

We summarize our submission to Sub-Challenge 1: W4A4 Quantization for Inference (HiF4 / MXFP4) of the ICME 2026 Low-Bit-width Large-Model Quantization Challenge. The sub-challenge targets 4-bit weight and 4-bit activatio…

Tail-Aware Post-Training Quantization for 3D Geometry Models

2026-02-02 · Sicheng Pan, Chen Tang, Shuzhao Xie, Ke Yang 외 arxiv

The burgeoning complexity and scale of 3D geometry models pose significant challenges for deployment on resource-constrained platforms. While Post-Training Quantization (PTQ) enables efficient inference without retrainin…