# Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs

arXiv: https://arxiv.org/abs/2410.16135 · HTML: https://mlsanity.com/paper/2410.16135/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 30 of 36)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch](https://mlsanity.com/paper/2102.04010/) (2021)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [Patch Slimming for Efficient Vision Transformers](https://mlsanity.com/paper/2106.02852/) (2021)
- [RPTQ: Reorder-based Post-training Quantization for Large Language Models](https://mlsanity.com/paper/2304.01089/) (2023)
- [Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks](https://mlsanity.com/paper/2102.08124/) (2021)
- [Vision Transformer Pruning](https://mlsanity.com/paper/2104.08500/) (2021)
- [Unified Visual Transformer Compression](https://mlsanity.com/paper/2203.08243/) (2022)
- [Global Vision Transformer Pruning with Hessian-Aware Saliency](https://mlsanity.com/paper/2110.04869/) (2021)
- [Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space](https://mlsanity.com/paper/2201.00814/) (2022)
- [Training Your Sparse Neural Network Better with Any Mask](https://mlsanity.com/paper/2206.12755/) (2022)
- [STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition](https://mlsanity.com/paper/2302.01172/) (2023)
- [Improving Convergence and Generalization Using Parameter Symmetries](https://mlsanity.com/paper/2305.13404/) (2023)
- [Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization](https://mlsanity.com/paper/2102.01670/) (2021)
- [Boost Vision Transformer with GPU-Friendly Sparsity and Quantization](https://mlsanity.com/paper/2305.10727/) (2023)
- [Pruning Large Language Models with Semi-Structural Adaptive Sparse Training](https://mlsanity.com/paper/2407.20584/) (2024)
- [Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers](https://mlsanity.com/paper/2402.04744/) (2024)

## Built on by (most cited first, 2 of 2)

- [From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction](https://mlsanity.com/paper/2507.03052/) (2025)
- [One Loop, Two Gains: Can Active Learning win the Lottery for Free?](https://mlsanity.com/paper/2609.10311/) (2026)

## Abstract (arXiv)

To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups (≤ 1.3) and requires fixed sparse ratios, meaning that other ratios, such as 4:8, 8:16, or those exceeding 50% sparsity, do not incur any speedups on GPUs. Recent studies suggest that V:N:M sparsity is promising in addressing these limitations of 2:4 sparsity. However, regarding accuracy, the effects of V:N:M sparsity on broader Transformer models, such as vision Transformers and large language models (LLMs), are largely unexamined. Moreover, Some specific issues related to V:N:M sparsity, such as how to select appropriate V and M values, remain unresolved. In this study, we thoroughly investigate the application of V:N:M sparsity in vision models and LLMs across multiple tasks, from pertaining to downstream tasks. We propose three key approaches to enhance the applicability and accuracy of V:N:M-sparse Transformers, including heuristic V and M selection, V:N:M-specific channel permutation, and three-staged LoRA training techniques. Experimental results show that, with our methods, the DeiT-small achieves lossless accuracy at 64:2:5 sparsity, while the DeiT-base maintains accuracy even at 64:2:8 sparsity. In addition, the fine-tuned LLama2-7B at 64:2:5 sparsity performs comparably or better than training-free 2:4 sparse alternatives on downstream tasks. More importantly, V:N:M-sparse Transformers offer a wider range of speedup-accuracy trade-offs compared to 2:4 sparsity. Overall, our exploration largely facilitates the V:N:M sparsity to act as a truly effective acceleration solution for Transformers in cost-sensitive inference scenarios.