QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm

• URL: http://arxiv.org/abs/2506.12355v1
• Date: Sat, 14 Jun 2025 05:38:19 GMT
• Title: QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm
• Authors: Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Chen Zhao, Yunji Chen,
• Abstract summary: We propose an LLM-friendly Thinking Language (LLM-TL) to help LLMs decouple the generation of high-level optimization logic and low-level implementation on GPU.<n>Along with a 2-stage reasoning workflow, TL-Code generation and translation, the LLMs can automatically generate FlashAttention implementation on diverse GPU.
• Score: 24.09018606185114
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely used and effective GPU-aware acceleration algorithm, it must require time-consuming and hardware-specific manual implementation, limiting adaptability across GPU architectures. Existing LLMs have shown a lot of promise in code generation tasks, but struggle to generate high-performance attention code. The key challenge is it cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance. To address the above challenge, we propose an LLM-friendly Thinking Language (LLM-TL) to help LLMs decouple the generation of high-level optimization logic and low-level implementation on GPU, and enhance LLMs' understanding of attention operator. Along with a 2-stage reasoning workflow, TL-Code generation and translation, the LLMs can automatically generate FlashAttention implementation on diverse GPUs, establishing a self-optimizing paradigm for generating high-performance attention operators in attention-centric algorithms. Verified on A100, RTX8000, and T4 GPUs, the performance of our methods significantly outshines that of vanilla LLMs, achieving a speed-up of up to 35.16x. Besides, our method not only surpasses human-optimized libraries (cuDNN and official library) in most scenarios but also extends support to unsupported hardware and data types, reducing development time from months to minutes compared with human experts.

Related papers

• GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization [0.18416014644193066]
  " GPU Kernel Scientist" is an automated methodology for iteratively refining accelerator kernels.<n>Our methodology employs LLMs in a multi-stage, evolutionary process.<n>We detail how this approach navigates the challenges of the AMD MI300 target architecture.
  arXiv  Detail & Related papers  (2025-06-25T19:59:34Z)
• CUDA-LLM: LLMs Can Write Efficient CUDA Kernels [9.287036563375617]
  Large Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation.<n>We propose a novel framework called textbfFeature SearchReinforcement (FSR) FSR jointly optimize compilation and functional correctness.
  arXiv  Detail & Related papers  (2025-06-10T10:51:03Z)
• NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding [54.88765757043535]
  This work rethinks data structures for statistical n-gram language models to enable fast and parallel operations for GPU-optimized inference.<n>Our approach, named NGPU-LM, introduces customizable greedy decoding for all major ASR model types with less than 7% computational overhead.<n>The proposed approach can eliminate more than 50% of the accuracy gap between greedy and beam search for out-of-domain scenarios while avoiding significant slowdown caused by beam search.
  arXiv  Detail & Related papers  (2025-05-28T20:43:10Z)
• Ramp Up NTT in Record Time using GPU-Accelerated Algorithms and LLM-based Code Generation [11.120838175165986]
  Homomorphic encryption (HE) is a core building block in privacy-preserving machine learning (PPML)<n>Many GPU-accelerated cryptographic schemes have been proposed to improve the performance of HE.<n>Given the powerful code generation capabilities of large language models (LLMs), we aim to explore their potential to automatically generate practical GPU-friendly algorithm code.
  arXiv  Detail & Related papers  (2025-02-16T12:53:23Z)
• HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models [1.2180334969164464]
  Large Language Models (LLMs) have revolutionized natural language processing by understanding and generating human-like text.<n>This paper introduces Hardware Accelerated Decoding (HADES), a novel approach to enhance the performance and energy efficiency of LLMs.
  arXiv  Detail & Related papers  (2024-12-27T21:19:01Z)
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution [114.61347672265076]
  Development of MLLMs for real-world robots is challenging due to the typically limited computation and memory capacities available on robotic platforms. We propose a Dynamic Early-Exit Framework for Robotic Vision-Language-Action Model (DeeR) that automatically adjusts the size of the activated MLLM. DeeR demonstrates significant reductions in computational costs of LLM by 5.2-6.5x and GPU memory of LLM by 2-6x without compromising performance.
  arXiv  Detail & Related papers  (2024-11-04T18:26:08Z)
• Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference [19.167604927651073]
  Auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. We propose a novel parallel prompt decoding that requires only $0.0002$% trainable parameters, enabling efficient training on a single A100-40GB GPU in just 16 hours. Our approach demonstrates up to 2.49$times$ speedup and maintains a minimal memory overhead of just $0.0004$%.
  arXiv  Detail & Related papers  (2024-05-28T22:19:30Z)
• Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment [56.44025052765861]
  Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs. We show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x.
  arXiv  Detail & Related papers  (2024-05-06T16:03:32Z)
• Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers [66.823588073584]
  Large language models (LLMs) have shown remarkable instruction-following capabilities and achieved impressive performances in various applications. Recent work has used the query-efficient Bayesian optimization (BO) algorithm to automatically optimize the instructions given to black-box LLMs. We propose a neural bandit algorithm which replaces the GP in BO by an NN surrogate to optimize instructions for black-box LLMs.
  arXiv  Detail & Related papers  (2023-10-02T02:01:16Z)
• FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs [57.12856172329322]
  We envision a decentralized system unlocking the potential vast untapped consumer-level GPU. This system faces critical challenges, including limited CPU and GPU memory, low network bandwidth, the variability of peer and device heterogeneity.
  arXiv  Detail & Related papers  (2023-09-03T13:27:56Z)
• PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives [55.79741270235602]
  We present compiler algorithms to automatically generate high performance implementations of Deep Learning primitives. We develop novel data reuse analysis algorithms using the polyhedral model. We also show that such a hybrid compiler plus a minimal library-use approach results in state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-06-02T06:44:09Z)

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.