STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU

• URL: http://arxiv.org/abs/2607.09385v1
• Date: Fri, 10 Jul 2026 13:09:47 GMT
• Title: STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU
• Abstract summary: We present STEEL, the first open-source implementation of FlashAttention targeting XDNA-like neural processing engines (NPUs)<n> STEEL reduces energy consumption by an average of 9.17x and 1.75x relative to CPU and GPU baselines, respectively.<n>On XDNA 1, STEEL achieves an average 9.6x latency reduction over the prior state of the art, and delivers a 22.8x speedup on average compared to a layer-by-layer attention implementation on XDNA 2.
• Score: 17.901016888350735
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The growing adoption of large language model-based agents within operating system workflows has increased the importance of energy-efficient inference on laptop-class systems-on-chip (SoCs). While cloud offloading remains common, it introduces reliability and privacy concerns that are particularly problematic for agentic workloads. Recent laptop SoCs, therefore, incorporate neural processing engines (NPUs) optimized for energy efficiency; however, effectively mapping attention mechanisms onto NPUs remains challenging due to architectural diversity and explicit data-movement programming models. In this work, we present STEEL, the first open-source implementation of FlashAttention targeting XDNA-like NPUs. STEEL introduces a dataflow formulation of prefill attention, enabling efficient exploitation of spatial parallelism and on-chip memory. Furthermore, STEEL addresses the load imbalance induced by the causal mask by leveraging a sparsity-aware pipeline placement onto the NPU array, reducing synchronization overhead and improving utilization. We evaluate STEEL on the AMD Ryzen AI 9 HX 370 SoC and compare its performance against optimized CPU and GPU implementations. Experimental results show that STEEL reduces energy consumption by an average of 9.17x and 1.75x relative to CPU and GPU baselines, respectively. On XDNA 1, STEEL achieves an average 9.6x latency reduction over the prior state of the art, and delivers a 22.8x speedup on average compared to a layer-by-layer attention implementation on XDNA 2.

Related papers

• Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference [29.72164316945472]
  Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks.<n>But their inference cost remains prohibitively high due to the quadratic complexity of attention and the memory bandwidth limitations of high-precision operations.<n>We present a low-bit mixed-precision attention kernel using the microscaling floating-point (MXFP) data format.
  arXiv  Detail & Related papers  (2026-04-05T03:56:21Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• eIQ Neutron: Redefining Edge-AI Inference with Integrated NPU and Compiler Innovations [4.776283807742058]
  eIQ Neutron efficient-NPU is integrated into a commercial flagship MPU.<n>Our solution achieves an average speedup of 1.8x (4x peak) at equal TOPS and memory resources across standard AI-benchmarks.
  arXiv  Detail & Related papers  (2025-09-17T19:45:51Z)
• Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative [31.74122603714625]
  Mixture of Experts (MoE) architecture enhances model capacity through sparse activation.<n>MoE faces two major difficulties in practical deployment.<n>Under limited memory, efficient offloading and collaborative inference of expert modules struggle to balance latency and throughput.<n>This paper proposes an efficient MoE edge deployment scheme based on Hessian-Aware Quantization (HAQ) and CPU- GPU collaborative inference.
  arXiv  Detail & Related papers  (2025-08-10T12:59:57Z)
• Pushing the Envelope of LLM Inference on AI-PC [45.081663877447816]
  ultra-low-bit models (1/1.58/2-bit) match the perplexity and end-task performance of their full-precision counterparts using the same model size.<n>The computational efficiency of state-of-the-art inference runtimes (e.g. bitnet) used to deploy them remains underexplored.<n>We take a bottom-up approach: we first design and implement 1-bit and 2-bit microkernels optimized for modern CPUs, achieving peak computational efficiency.<n>We present end-to-end inference results with 2-bit models that outperform the current SOTA runtime bitnet
  arXiv  Detail & Related papers  (2025-08-08T23:33:38Z)
• Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computing [67.98609858326951]
  Intra-DP is a high-performance collaborative inference system optimized for deep neural networks (DNNs) on mobile devices.<n>It reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.<n>The evaluation demonstrates that Intra-DP reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-07-08T09:50:57Z)
• GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units [0.6063137165121326]
  Graph Neural Networks (GNNs) are vital for learning from graph-structured data, enabling applications in network analysis, recommendation systems, and speech analytics.<n>GraNNite is the first hardware-aware framework optimizing GNN execution on commercial-off-the-shelf (COTS) SOTA accelerators.
  arXiv  Detail & Related papers  (2025-02-10T17:03:02Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference [82.1584439276834]
  Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. We present EdgeBERT, an in-depth algorithm- hardware co-design for latency-aware energy optimization for multi-task NLP.
  arXiv  Detail & Related papers  (2020-11-28T19:21:47Z)

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.