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

• URL: http://arxiv.org/abs/2605.26628v1
• Date: Tue, 26 May 2026 07:04:22 GMT
• Title: Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2
• Abstract summary: This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge.<n>We quantize the main linear layers in both Wan2.2 transformer modules with W4A4 HiFloat4 fake quantization.<n>This design reduces the influence of rare outlier calibrations while keeping the runtime HiFloat4 arithmetic and sampling pipeline unchanged.
• Score: 45.26076445356586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks [51.21235018272886]
  Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete.<n>We propose PTQ4SNN, a membrane-aware post-training quantization framework that jointly quantizes weights and recurrent membrane states using only a small calibration set.<n>Experiments on static and event-based classification and semantic segmentation show that PTQ4SNN effectively preserves model accuracy under W4 quantization and approximately 4-bit membrane precision.
  arXiv  Detail & Related papers  (2026-08-07T10:16:25Z)
• W4A4 Quantization for Inference on Wan2.2-I2V-A14B [23.122181646076882]
  Sub-challenge targets 4-bit weight and 4-bit activation inference on Wan-AI/Wan2.2-I2V-A14B under HiF4 or MXFP4 numerical formats.<n>We adapt two complementary ideas from LLM quantization, MixQ-style mixed precision for sparse activation outliers and SmoothQuant-style per-channel smoothing.<n>On official VBench I2V metrics, our pipeline stays within 2-3.5 percent of FP16 on most quality axes and improves motion smoothness.
  arXiv  Detail & Related papers  (2026-06-28T11:12:52Z)
• Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V [23.570323694430538]
  W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges.<n>These difficulties are compounded by Wan2.2-I2V's two-expert Mixture-of-Experts DiT design.<n>We propose a post-training quantization framework combining SVDQuant-based low-rank outlier compensation, GPTQ-based reconstruction-aware residual weight quantization, and timestep-bin-wise per-layer activation clipping-ratio search conducted independently for each expert.
  arXiv  Detail & Related papers  (2026-05-26T13:24:01Z)
• Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation [40.140261007984215]
  We improve the state of the art for quantized training in NVFP4 via a novel unbiased quantization routine for micro-scaled formats.<n>We show analytically that Quartet II achieves consistently better gradient estimation across all major matrix multiplications.
  arXiv  Detail & Related papers  (2026-01-30T10:39:11Z)
• ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers [21.65616995056907]
  As model size increases, the growing memory footprint and inference latency pose significant challenges for practical deployment.<n>Recent studies in large language models (LLMs) show that rotation-based techniques can smooth outliers and enable 4-bit quantization.<n>We propose ConvRot, a group-wise rotation-based quantization method that leverages regular Hadamard transform (RHT) to suppress both row-wise and column-wise outliers.
  arXiv  Detail & Related papers  (2025-12-03T11:02:16Z)
• Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization [77.67818998672516]
  We present the first comprehensive study of MXFP4 and NVFP4 for post-training quantization.<n>We introduce Micro-Rotated-GPTQ (MR-GPTQ), a variant of the classic GPTQ quantization algorithm.<n>We show that MR-GPTQ matches or outperforms state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2025-09-27T09:22:21Z)
• FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers [15.324769026957641]
  Post-training quantization is a lightweight method to alleviate burdens without the need for training or fine-tuning.<n>We introduce FP4DiT, a PTQ method that leverages Floating-Point Quantization to achieve W4A6 quantization.<n> Experimental results demonstrate that FP4DiT outperforms integer-based PTQ at W4A6 and W4A8 precision.
  arXiv  Detail & Related papers  (2025-03-19T17:44:21Z)
• PTQ4DiT: Post-training Quantization for Diffusion Transformers [52.902071948957186]
  Post-training Quantization (PTQ) has emerged as a fast and data-efficient solution that can significantly reduce computation and memory footprint. We propose PTQ4DiT, a specifically designed PTQ method for DiTs. We demonstrate that our PTQ4DiT successfully quantizes DiTs to 8-bit precision while preserving comparable generation ability.
  arXiv  Detail & Related papers  (2024-05-25T02:02:08Z)
• Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization [62.15918574997175]
  It is known that language models contain outlier channels whose values on average are orders of magnitude higher than other channels. We propose a strategy which regularizes a layer's inputs via quantization-aware training (QAT) and its outputs via activation kurtosis regularization. We show that regularizing both the inputs and outputs is crucial for preventing a model's "migrating" the difficulty in input quantization to the weights.
  arXiv  Detail & Related papers  (2024-04-04T17:25:30Z)
• Towards Accurate Post-Training Quantization for Vision Transformer [48.779346466374406]
  Existing post-training quantization methods still cause severe performance drops. APQ-ViT surpasses the existing post-training quantization methods by convincing margins.
  arXiv  Detail & Related papers  (2023-03-25T03:05:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.