ELiTeFormer: An Efficient Transformer for FPGAs

• URL: http://arxiv.org/abs/2607.03652v1
• Date: Sat, 04 Jul 2026 00:52:06 GMT
• Title: ELiTeFormer: An Efficient Transformer for FPGAs
• Abstract summary: Transformer blocks are prevalent in large language model (LLM) but present deployment challenges.<n>We present ELiTeFormer, the first Transformer model architecture that unifies hybrid linear attention with ultra-low-precision (ternary) linear projections.
• Score: 3.884894816711594
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer blocks are prevalent in large language model (LLM) but present deployment challenges due to their challenging computational and memory demands. While prior work has typically optimized attention mechanisms or feed-forward networks (FFNs) separately, few hardware (HW) architecture have jointly addressed both components with co-designed hardware acceleration. We present ELiTeFormer (Efficient Linear Ternary Transformer), the first Transformer model architecture that unifies hybrid linear attention with ultra-low-precision (ternary) linear projections, specifically co-designed for field-programmable gate array (FPGA) deployment. ELiTeFormer achieves 10x model weight compression and 12.8x key-value (KV) cache compression compared to LLaMA 3, while maintaining competitive accuracy (31.9% on the MMLU benchmark, within 3.0% of BitNet b1.58). Our key architectural contribution is a novel processing element (PE) micro-architecture that eliminates all multiplications in ternary linear projections through bitmasking operations, significantly reducing resource utilization by completely avoiding dedicated digital signal processing (DSP) blocks. We simulate, synthesize, and deploy ELiTeFormer targeting a Xilinx VCK5000 Versal board using high-level synthesis (HLS) flows. Block-level simulations show 9.6x speedup for FFN operations and 4.4x speedup for attention compared to standard implementations. End-to-end deployment achieves up to 3.9x lower latency and 3.2x better energy efficiency than LLaMA 3 on an NVIDIA A100 graphics processing unit (GPU) at long context lengths. This represents the first FPGA realization combining linear attention with ternary quantization, demonstrating the viability of algorithm-architecture co-design for next-generation LLM acceleration.

Related papers

• OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond [50.440302567029654]
  Multi-modal intelligence has made the Key-Value cache a dominant memory bottleneck for efficient deployment.<n>In this work, we revisit the inherent limitations of the per-channel quantization paradigm.<n>We propose OScaR, an accurate and lightweight KV cache compression framework for X-LLMs.
  arXiv  Detail & Related papers  (2026-05-19T10:53:03Z)
• BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design [71.97035034203275]
  We analyze zero-point distortion in binarization and propose a Binary Weights & Ternary Activations (BWTA) quantization scheme.<n>For training, we propose Smooth Multi-Stage Quantization, combining a Levelwise Degradation Strategy and a MagnitudeAlignment Projection Factor.<n>Experiments show that BWTA approaches full-precision performance for Transformer-based models, with an average 3.5% drop on GLUE and less than 2% drop on five tasks.
  arXiv  Detail & Related papers  (2026-04-05T04:25:07Z)
• 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)
• AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design [3.64182026498686]
  Large language models (LLMs) have achieved huge success in the natural language processing (NLP) field.<n>We propose AccLLM, a comprehensive acceleration framework that enables efficient and fast long-context LLM inference.<n>We validate AccLLM on the Xilinx Alveo U280 FPGA, demonstrating a 4.07x energy efficiency and a 2.98x throughput.
  arXiv  Detail & Related papers  (2025-04-07T02:52:30Z)
• Design and Implementation of an FPGA-Based Hardware Accelerator for Transformer [0.0]
  Transformer-based large language models rely heavily on matrix multiplications for attention and feed-forward layers.<n>We introduce a highly optimized tiled matrix multiplication accelerator on a resource-constrained Xilinx KV260 FPGA.<n>Our design exploits persistent on-chip storage, a robust two-level tiling strategy for maximal data reuse, and a systolic-like unrolled compute engine.
  arXiv  Detail & Related papers  (2025-03-20T22:15:42Z)
• Runtime Tunable Tsetlin Machines for Edge Inference on eFPGAs [0.2294388534633318]
  eFPGAs allow for the design of hardware accelerators of edge Machine Learning (ML) applications at a lower power budget.<n>The limited eFPGA logic and memory significantly constrain compute capabilities and model size.<n>The proposed eFPGA accelerator focuses on minimizing resource usage and allowing flexibility for on-field recalibration over throughput.
  arXiv  Detail & Related papers  (2025-02-10T12:49:22Z)
• SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs [3.302913401404089]
  Sliding window-based static sparse attention mitigates the problem by limiting the attention scope of the input tokens. We propose a dataflow-aware FPGA-based accelerator design, SWAT, that efficiently leverages the sparsity to achieve scalable performance for long input.
  arXiv  Detail & Related papers  (2024-05-27T10:25:08Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts [60.1586169973792]
  M$3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE) MoE achieves better accuracy and over 80% reduction computation but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations.
  arXiv  Detail & Related papers  (2023-05-30T02:24:03Z)
• Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design [66.39546326221176]
  Attention-based neural networks have become pervasive in many AI tasks. The use of the attention mechanism and feed-forward network (FFN) demands excessive computational and memory resources. This paper proposes a hardware-friendly variant that adopts a unified butterfly sparsity pattern to approximate both the attention mechanism and the FFNs.
  arXiv  Detail & Related papers  (2022-09-20T09:28:26Z)

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.