Related papers: TRINE: A Token-Aware, Runtime-Adaptive FPGA Infere…

With the development of deep neural network (DNN) enabled applications, achieving high hardware resource efficiency on diverse workloads is non-trivial in heterogeneous computing platforms. Prior works discuss dedicated architectures to…

With the emergence of wearable devices and other embedded systems, deploying large language models (LLMs) on edge platforms has become an urgent need. However, this is challenging because of their high computational and memory demands.…

Recent years have seen a paradigm shift towards multi-task learning. This calls for memory and energy-efficient solutions for inference in a multi-task scenario. We propose an algorithm-hardware co-design approach called MIME. MIME reuses…

Driven by the increasing demand for low-latency and real-time processing, machine learning applications are steadily migrating toward edge computing platforms, where Field-Programmable Gate Arrays (FPGAs) are widely adopted for their energy…

As deep neural network (DNN) models are growing exponentially in size, their deployment on resource-constrained edge platforms is becoming increasingly challenging. In-memory-computing (IMC) with non-volatile memories (NVMs) has emerged as…

This work focuses on an efficient Agile design methodology for domain-specific accelerators. We employ feature-by-feature enhancement of a vertical development stack and apply it to the TVM/VTA inference accelerator. We have enhanced the…

This work presents TREA, a low-precision time-multiplexed and resource-efficient edge-AI accelerator for object detection and classification, targeting stringent area-power-latency constraints of edge vision platforms. The proposed…

Vision Transformer (ViT) acceleration with field programmable gate array (FPGA) is promising but challenging. Existing FPGA-based ViT accelerators mainly rely on temporal architectures, which process different operators by reusing the same…

The rapid adoption of large language models and multimodal foundation models has made multimodal data preparation pipelines critical AI infrastructure. These pipelines interleave CPU-heavy preprocessing with accelerator-backed (GPU/NPU/TPU)…

The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated by intermittent…

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear mixers, along with standard…

With new accelerator hardware for DNN, the computing power for AI applications has increased rapidly. However, as DNN algorithms become more complex and optimized for specific applications, latency requirements remain challenging, and it is…

Overlays have shown significant promise for field-programmable gate-arrays (FPGAs) as they allow for fast development cycles and remove many of the challenges of the traditional FPGA hardware design flow. However, this often comes with a…

Deploying Large Language Models (LLMs) on resource-constrained edge devices faces critical bottlenecks in memory bandwidth and power consumption. While ternary quantization (e.g., BitNet b1.58) significantly reduces model size, its direct…

This paper introduces TINA, a novel framework for implementing non Neural Network (NN) signal processing algorithms on NN accelerators such as GPUs, TPUs or FPGAs. The key to this approach is the concept of mapping mathematical and logic…

While iterative stereo matching achieves high accuracy, its dependence on Recurrent Neural Networks (RNN) hinders edge deployment, a challenge underexplored in existing researches. We analyze iterative refinement and reveal that disparity…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Standardized DNN models that have been proved to perform well on machine learning tasks are widely used and often adopted as-is to solve downstream tasks, forming the transfer learning paradigm. However, when serving multiple instances of…

Apple Neural Engine (ANE) is a dedicated neural processing unit (NPU) present in every Apple Silicon chip. Mixture-of-Experts (MoE) LLMs improve inference efficiency via sparse activation but are challenging for NPUs in three ways: expert…

Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…