6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models

Rundong Su; Jintao Zhang; Zhihang Yuan; Haojie Duanmu; Jianfei Chen; Jun Zhu

cs.CVMar 19, 2026

6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models

Authors: Rundong Su, Jintao Zhang, Zhihang Yuan, Haojie Duanmu, Jianfei Chen, Jun Zhu

Organizations: Fudan University · Tsinghua University · Shanghai Jiao Tong University

Abstract

Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical way to reduce memory usage and boost computation speed. Existing quantization methods typically apply a static bit-width allocation, overlooking the quantization difficulty of activations across diffusion timesteps, leading to a suboptimal trade-off between efficiency and quality. In this paper, we propose a inference time NVFP4/INT8 Mixed-Precision Quantization framework. We find a strong linear correlation between a block's input-output difference and the quantization sensitivity of its internal linear layers. Based on this insight, we design a lightweight predictor that dynamically allocates NVFP4 to temporally stable layers to maximize memory compression, while selectively preserving INT8 for volatile layers to ensure robustness. This adaptive precision strategy enables aggressive quantization without compromising generation quality. Beside this, we observe that the residual between the input and output of a Transformer block exhibits high temporal consistency across timesteps. Leveraging this temporal redundancy, we introduce Temporal Delta Cache (TDC) to skip computations for these invariant blocks, further reducing the computational cost. Extensive experiments demonstrate that our method achieves 1.92 $\times$ end-to-end acceleration and 3.32 $\times$ memory reduction, setting a new baseline for efficient inference in Video DiTs.

Figures & tables

Figure 1: Relative L2 quantization error(defined in Eq. 4 ) of individual linear layers in CogVideoX [ 38 ] across denoising timesteps. The severe temporal fluctuations demonstrate that activation sensitivity to quantization is highly dynamic, highlighting the limitations of static mixed-precision policies.

Figure 2: Overview of our proposed methods. We using DMPQ to decide the quantization bits of each linear layer activation based on the block preceding timestep input output relative L1 loss $\Gamma$ . And using TDC to decide whether to skip block computation based on preceding two timesteps block updates $\Delta$ .

Figure 3: The linear relationship between the block-level input-output relative L1 distance at the previous timestep ( $\Gamma_{t-1}$ ) and the layer-wise relative quantization error ( $E_{rel}$ ) at the current timestep. The data points are collected by executing the diffusion model over a calibration set. For each block, we extract the time-shifted valid data pairs across all timesteps to perform linear regression ( $y=\alpha x+\beta$ ) for each internal linear layer.

Figure 4: Temporal redundancy of Transformer block updates in Video DiTs. We visualize the Cosine Similarity (left) and Relative L2 Difference (right) of the residual updates ( $\Delta_{t}^{l}$ and $\Delta_{t-1}^{l}$ ) between adjacent timesteps. The inherently high similarity across most timesteps and layers motivates our adaptive Temporal Delta Cache.

Figure 5: Visual comparisons between ours and FP16 baseline [ 38 ] ), together with quantization methods [ 1 ] , SmoothQuant [ 37 ] and ViDiT-Q [ 51 ]

Method	Bit-width	Aesthetic	BG.	Overall	Dynamic	Subject	Imaging	Scene	Motion
	(W/A)	Quality	Consist.	Consist.	Degree	Consist.	Quality	Consist.	Smooth.
CogVideo-2B
Original	W16/A16	0.5464	0.9500	0.2423	0.7639	0.9491	0.5713	0.3590	0.9714
SmoothQuant	W4A8	0.5332	0.9441	0.2473	0.6806	0.9319	0.5460	0.3343	0.9680
QuaRot	W4A8	0.5158	0.9427	0.2383	0.5139	0.9202	0.5258	0.2682	0.9715
ViDiT-Q	W4A8	0.5332	0.9449	0.2464	0.6528	0.9272	0.5534	0.3372	0.9692

Table 1: Performance comparison of various quantization methods on VBench using CogVideo-2B and CogVideo-5B.

Method	Bit-width	Speedup	Aesthetic	BG.	Overall	Dynamic	Subject	Imaging	Scene	Motion
	(W/A)		Quality	Consist.	Consist.	Degree	Consist.	Quality	Consist.	Smooth.
Original	W16A16	$1.00\times$	0.5464	0.9500	0.2423	0.7639	0.9491	0.5713	0.3590	0.9714
Ours(DMPQ)	W4A6	$1.36\times$	0.5437	0.9455	0.2474	0.6806	0.9282	0.5511	0.3307	0.9691
Ours(Full)	W4A6 ∗	$1.92\times$	0.5366	0.9421	0.2492	0.7083	0.9255	0.5369	0.3307	0.9691

Table 2: Performance evaluation of integrating TDC into DMPQ on VBench [ 9 ] .

Method	DMPQ	TDC	PDR	VQA-A $\uparrow$	VQA-T $\uparrow$	CLIP $\uparrow$	CLIP-T $\uparrow$	Flow Score $\uparrow$
Original (FP16)	-	-	-	74.6175	77.7548	0.1824	0.9973	5.8389
Uniform W4A4	-	-	-	68.9105	73.6116	0.1818	0.9974	4.2518
Uniform W4A8	-	-	-	71.2093	78.6070	0.1859	0.9972	5.3140
Ablation 1	✓			75.5332	77.8404	0.1814	0.9976	5.3266
Ablation 2		✓		72.2671	78.1517	0.1838	0.9975	5.7602
Ablation 3	✓	✓		73.7243	77.2833	0.1835	0.9978	4.7271

Table 3: Ablation Study of Proposed Components. Evaluation of Dynamic Mixed Precision Quantization (DMPQ), Temporal Delta Cache (TDC), and Purified Delta Refresh (PDR).

Diffusion Model Quantization

Diffusion model quantization compresses model weights and activations to reduce inference memory and latency while preserving generated image, video, and speech quality.

See all 39 papers

SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
Mar 3, 2026Wonsuk Jang, Thierry TambeDiffusion Model Quantization Neural Network Quantization
Stanford University
Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers
Oct 26, 2026Yeonjae Kim, Omin Kwon, Seong Hoon Seo +1Diffusion Model Inference Acceleration Video Diffusion Models
Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea.
DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention
Sep 26, 2026Rui Ding, Haopeng Li, Weize Ma +10Video Diffusion Models Diffusion Model Inference Acceleration
Nanjing University · HKUST(GZ) · Duke University +3

Mar 3, 2026J/K move · Enter open · S save

SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers

Wonsuk Jang, Thierry Tambe

Stanford University

Diffusion Model Quantization Neural Network Quantization Activation Quantization Video Diffusion Models Diffusion Transformer

Open paper AskPDF arXiv

Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video quality due to high activation variation and the difficulty of preserving semantic and temporal coherence. We propose SemanticDialect, which advances block-wise mixed-format quantization. In this framework, each block selects an optimal format (dialect) from a candidate set (formatbook), which is augmented with lookup tables that store quantization errors and quantized indices, enabling efficient per-block format selection and quantization with minimal online overhead. We further introduce attention-guided activation decomposition, which reduces quantization error via residual quantization, and semantic-aware dialect assignment (SeDA), which reduces cross-token quantization inconsistency by enforcing format uniformity among semantically correlated tokens. Experiments demonstrate that SemanticDialect outperforms prior quantization methods and block-wise formats (MXFP4, NVFP4) while approaching FP16 quality on Open-Sora 2.0. We also validate hardware deployability through RTL design and GPU kernel implementation.

Abstract

Diffusion Model Quantization

Explore similar work

SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers

Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers

DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention