Prefill/Decode-Aware Evaluation of LLM Inference on Emerging AI Accelerators

As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, inference efficiency has become a central systems challenge. While GPUs dominate current deployments, a growing number of AI accelerators claim advantages for LLM inference, yet it remains unclear under which conditions such accelerators outperform GPUs in practice. Recent inference systems decompose execution into Prefill and Decode phases, which exhibit distinct computational characteristics and latency metrics, commonly captured by time to first token (TTFT) and time per output token (TPOT). This paper presents a phase-aware evaluation of LLM inference performance across GPUs and emerging AI accelerators using a common model, Llama2-7B. By separately measuring Prefill and Decode performance, we reveal that accelerator advantages differ by phase and metric. Our results show that GPUs consistently excel in the compute-intensive Prefill phase, while GroqRack achieves significantly lower TPOT during Decode (batching not currently supported). However, GPUs regain an advantage in Decode throughput as batch size increases. These findings demonstrate that each platform exhibits distinct phase-dependent strengths. We further analyze heterogeneous Prefill/Decode disaggregation across different accelerator platforms, identifying performance gains and the workload and network conditions under which such gains are realized.

Intelligent IoT Attack Detection Design via ODLLM with Feature Ranking-based Knowledge Base

The widespread adoption of Internet of Things (IoT) devices has introduced significant cybersecurity challenges, particularly with the increasing frequency and sophistication of Distributed Denial of Service (DDoS) attacks. Traditional machine learning (ML) techniques often fall short in detecting such attacks due to the complexity of blended and evolving patterns. To address this, we propose a novel framework leveraging On-Device Large Language Models (ODLLMs) augmented with fine-tuning and knowledge base (KB) integration for intelligent IoT network attack detection. By implementing feature ranking techniques and constructing both long and short KBs tailored to model capacities, the proposed framework ensures efficient and accurate detection of DDoS attacks while overcoming computational and privacy limitations. Simulation results demonstrate that the optimized framework achieves superior accuracy across diverse attack types, especially when using compact models in edge computing environments. This work provides a scalable and secure solution for real-time IoT security, advancing the applicability of edge intelligence in cybersecurity.

Case Study: Leveraging GenAI to Build AI-based Surrogates and Regressors for Modeling Radio Frequency Heating in Fusion Energy Science

This work presents a detailed case study on using Generative AI (GenAI) to develop AI surrogates for simulation models in fusion energy research. The scope includes the methodology, implementation, and results of using GenAI to assist in model development and optimization, comparing these results with previous manually developed models.

Quantum pixel representations and compression for $N$-dimensional images

We introduce a novel and uniform framework for quantum pixel representations that overarches many of the most popular representations proposed in the recent literature, such as (I)FRQI, (I)NEQR, MCRQI, and (I)NCQI. The proposed QPIXL framework results in more efficient circuit implementations and significantly reduces the gate complexity for all considered quantum pixel representations. Our method only requires a linear number of gates in terms of the number of pixels and does not use ancilla qubits. Furthermore, the circuits only consist of Ry gates and CNOT gates making them practical in the NISQ era. Additionally, we propose a circuit and image compression algorithm that is shown to be highly effective, being able to reduce the necessary gates to prepare an FRQI state for example scientific images by up to 90% without sacrificing image quality. Our algorithms are made publicly available as part of QPIXL++, a Quantum Image Pixel Library.