Related papers: LoopLynx: A Scalable Dataflow Architecture for Eff…

Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of…

Large language model (LLM) pruning with fixed N:M structured sparsity significantly limits the expressivity of the sparse model, yielding sub-optimal performance. In contrast, supporting multiple N:M patterns to provide sparse…

The rapid adoption of large language models (LLMs) has led to significant advances in natural language processing and text generation. However, the energy consumed through LLM model inference remains a major challenge for sustainable AI…

In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Existing models are primarily based on the Transformer…

This work presents a novel reconfigurable architecture for Low Latency Graph Neural Network (LL-GNN) designs for particle detectors, delivering unprecedented low latency performance. Incorporating FPGA-based GNNs into particle detectors…

Executing machine learning inference tasks on resource-constrained edge devices requires careful hardware-software co-design optimizations. Recent examples have shown how transformer-based deep neural network models such as ALBERT can be…

To increase performance and efficiency, systems use FPGAs as reconfigurable accelerators. A key challenge in designing these systems is partitioning computation between processors and an FPGA. An appropriate division of labor may be…

This paper presents GraphAGILE, a domain-specific FPGA-based overlay accelerator for graph neural network (GNN) inference. GraphAGILE consists of (1) \emph{a novel unified architecture design} with an \emph{instruction set}, and (2) \emph{a…

Recurrent Neural Networks (RNNs) are vital for sequential data processing. Long Short-Term Memory Autoencoders (LSTM-AEs) are particularly effective for unsupervised anomaly detection in time-series data. However, inherent sequential…

The LCLS2 Free Electron Laser FEL will generate xray pulses to beamline experiments at up to 1Mhz These experimentals will require new ultrahigh rate UHR detectors that can operate at rates above 100 kHz and generate data throughputs…

Recurrent neural networks have been shown to be effective architectures for many tasks in high energy physics, and thus have been widely adopted. Their use in low-latency environments has, however, been limited as a result of the…

Serving generative inference of the large language model is a crucial component of contemporary AI applications. This paper focuses on deploying such services in a heterogeneous and cross-datacenter setting to mitigate the substantial…

Hybrid memory systems, comprised of emerging non-volatile memory (NVM) and DRAM, have been proposed to address the growing memory demand of applications. Emerging NVM technologies, such as phase-change memories (PCM), memristor, and 3D…

State space models (SSMs) like Mamba have recently attracted much attention. Compared to Transformer-based large language models (LLMs), Mamba achieves linear computation complexity with the sequence length and demonstrates superior…

Disaggregating the prefill and decoding phases represents an effective new paradigm for generative inference of large language models (LLM), which eliminates prefill-decoding interference and optimizes resource allocation. However, it is…

As large language models (LLMs) continue to scale, the high power consumption of AI accelerators in datacenters presents significant challenges, substantially increasing the total cost of ownership (TCO) for cloud service providers (CSPs)…

Due to rising demands for Artificial Inteligence (AI) inference, especially in higher education, novel solutions utilising existing infrastructure are emerging. The utilisation of High-Performance Computing (HPC) has become a prevalent…

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems…

To process sensor data in the Internet of Things(IoTs), embedded deep learning for 1-dimensional data is an important technique. In the past, CNNs were frequently used because they are simple to optimise for special embedded hardware such…