Skip to content
#machine learning Review Open access

Recent developments in Transformer inference deployment on FPGA platforms: A survey

Aug 2026 · Journal of systems architecture · Vol 177, pp. 103841 · 0 citations · 67 references
Computer Science

TL;DR

This study investigates the most recent advances, trends, and design choices for Transformer inference on FPGA platforms, and performs a systematic literature review, extracting and delving into preferred techniques for implementation and optimisation.

Abstract

With the rapid and continuous growth in the incorporation of machine learning models based on the Transformer architecture, capable deployment is in high demand. In this context, capable deployment refers to operational performance aspects, e.g., throughput and latency, as well as efficiency aspects, e.g., energy consumption. When it comes to the task of inference using such models, purpose-built hardware accelerators provide a lucrative alternative to common deployment choices, such as Central Processing Units (CPUs) and Graphics Processing Units (GPUs). The Field Programmable Gate Array (FPGA) platforms category is an example of such alternative accelerators, promising implementation flexibility, energy efficiency, improved latency and suitability for on-site deployment. We investigate the most recent advances, trends, and design choices for Transformer inference on FPGA platforms. We perform a systematic literature review, extracting and delving into preferred techniques for implementation and optimisation. This study and the provided taxonomy of topics could act as a guide for researchers from the academia and industry alike.

Read PDF

Similar papers

Conference Aug 2026

Designing and Building an FPGA Accelerator That Uses Less Energy for DNN Inference

Deep Neural Networks (DNNs) are critical to modern AI applications, yet their deployment on standard CPUs and GPUs is constrained by high power consumption and computational latency, particularly in resource-constrained edge environments. To address these limitations, this paper presents the design and implementation o...

P. V. G. K. Rao, Dudekula Raziya · 0 citations
Review Aug 2026

Model Compression and Hardware-Aware Acceleration for Deep Learning on FPGAs: A Co-Design Taxonomy and Comparative Analysis

This survey restricted the scope to FPGAs alone and organized 25 compression-hardware co-design case studies into a five-category taxonomy defined by which FPGA resources each strategy primarily reshapes, formalizing six open challenges: toolchain fragmentation, accuracy--efficiency characterization, automated mixed-pr...

Peter Forcha, H. Kajekusumadhar, Mbua Peter et al. · 0 citations
Conference Aug 2026

An Efficient HLS-Based Hardware Accelerator with Resource Optimization for Transformer Models

Deploying Transformer models on FPGA and System-on-Chip (SoC) platforms remains challenging due to their substantial computational complexity, large memory footprint, and high hardware resource requirements, particularly in multi-head attention and stacked encoder-decoder layers. This paper proposes a hardware-efficien...

Xuan Thao Tran, Thi Diem Tran · 0 citations
Oct 2026

Efficient FPGA Acceleration of Deep Neural Networks for Image Processing Using an OpenCL-Based High-Level Synthesis Framework

This paper proposes a metrics-driven predictive methodology for FPGA-based DNN acceleration using an OpenCL-based high-level synthesis framework that validates how predictive modeling can help guide FPGA design choices in a way that improves both efficiency and portability for signal and image-processing-oriented DNN a...

Soufien Gdaim, Hachem Bensalem, Ghyslain Gagnon · 0 citations
Open access Aug 2026

A Compiler-Aware Framework for Partitioned Neural Network Inference on FPGA DPUs

This work analyzes the Vitis AI compiler and proposes an XIR-level splitting framework that generates independently compilable .xmodel fragments while preserving the context required for DPU mapping, and restores correct DPU mapping by addressing boundary-context loss and incomplete dependency collection.

Federico Buccellato, Luca Mannini, C. De Sio · 0 citations
Sep 2026

FPGA‐Based GRU Accelerator for Streaming Data Processing

In the evolving landscape of edge devices, unlocking artificial intelligence (AI) services via the cloud has consistently raised concerns related to energy consumption, latency, and privacy. Shifting these services locally onto edge devices powered by CPUs and GPUs have always been hindered by their limited storage a...

Doaa K. Hameed, Abdullah M. Zyarah · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.