Related papers: SHIELD: A Segmented Hierarchical Memory Architectu…

Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…

Large Language Models (LLMs) are increasingly deployed on edge devices with Neural Processing Units (NPUs), yet the decode phase remains memory-intensive, limiting performance. Processing-in-Memory (PIM) offers a promising solution, but…

Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and…

Split Learning (SL) recently emerged as an efficient paradigm for distributed Machine Learning (ML) suitable for the Internet Of Things (IoT)-Cloud systems. However, deploying SL on resource-constrained edge IoT platforms poses a…

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Machine learning (ML)-based methods have recently become attractive for detecting security vulnerability exploits. Unfortunately, state-of-the-art ML models like long short-term memories (LSTMs) and transformers incur significant…

Large Language Models (LLMs) are increasingly deployed in production, contributing towards shifting the burden in terms of computational resources and energy demands from training to inference. While prior work has examined the energy cost…

Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. Toward efficient wireless LLM inference in edge computing, this study comprehensively…

De-identification of clinical text remains essential for secondary use of electronic health records (EHRs), yet public benchmarks such as i2b2 2006/2014 are over a decade old and lack the semantic and demographic diversity of modern…

Host-based intrusion detection system (HIDS) is a key defense component to protect the organizations from advanced threats like Advanced Persistent Threats (APT). By analyzing the fine-grained logs with approaches like data provenance, HIDS…

Aggressively quantized large language models (LLMs), such as BitNet-style 1.58-bit Transformers with ternary weights, make it feasible to deploy generative AI on low-power edge FPGAs. However, as prompts grow to tens of thousands of tokens,…

Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted…

Large Language Models (LLMs) are increasingly deployed on converged Cloud and High-Performance Computing (HPC) infrastructure. However, as LLMs handle confidential inputs and are fine-tuned on costly, proprietary datasets, their heightened…

Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there…

Non-Intrusive Load Monitoring (NILM) enables the disaggregation of the global power consumption of multiple loads, taken from a single smart electrical meter, into appliance-level details. State-of-the-Art approaches are based on Machine…

Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs.…

Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of…

We introduce Glinthawk, an architecture for offline Large Language Model (LLM) inference. By leveraging a two-tiered structure, Glinthawk optimizes the utilization of the high-end accelerators ("Tier 1") by offloading the attention…

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware…

Large language models (LLMs) can solve challenging tasks. However, their inference computation on modern GPUs is highly inefficient due to the increasing number of tokens they must attend to as they generate new ones. To address this…