# Accelerating Sparse Transformer Inference on GPU

arXiv: https://arxiv.org/abs/2506.06095 · HTML: https://mlsanity.com/paper/2506.06095/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 80 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Efficient Content-Based Sparse Attention with Routing Transformers](https://mlsanity.com/paper/2003.05997/) (2020)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference](https://mlsanity.com/paper/2403.09054/) (2024)
- [A3: Accelerating Attention Mechanisms in Neural Networks with Approximation](https://mlsanity.com/paper/2002.10941/) (2020)
- [TurboTransformers: An Efficient GPU Serving System For Transformer Models](https://mlsanity.com/paper/2010.05680/) (2020)
- [DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion](https://mlsanity.com/paper/2108.13342/) (2021)
- [Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer](https://mlsanity.com/paper/2009.08605/) (2020)
- [ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design](https://mlsanity.com/paper/2210.09573/) (2022)
- [FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks](https://mlsanity.com/paper/2107.06419/) (2021)
- [ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs](https://mlsanity.com/paper/2210.03052/) (2022)
- [Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design](https://mlsanity.com/paper/2209.09570/) (2022)
- [FlashMask: Efficient and Rich Mask Extension of FlashAttention](https://mlsanity.com/paper/2410.01359/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask layers introduce sparsity into Transformer to reduce calculations. However, previous works rarely focus on the performance optimization of sparse Transformer. In addition, current static operator fusion schemes fail to adapt to diverse application scenarios. To address the above problems, we propose STOF, a framework that incorporates optimizations for Sparse Transformer that enables flexible masking and Operator Fusion on GPU. For multi-head attention (MHA) structure, STOF maps the computation to row-wise or blockwise kernels with unique storage formats according to analytical modeling. For downstream operators, STOF maps the fusion scheme to compilation templates and determines the optimal running configuration through two-stage searching. The experimental results show that compared to the stateof-the-art work, STOF achieves maximum speedups of 1.6x in MHA computation and 1.4x in end-to-end inference.