Related papers: Foundry: Template-Based CUDA Graph Context Materia…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

Diffusion models produce realistic images and videos but require substantial computational resources, necessitating multi-accelerator parallelism for real-time deployment. However, parallel inference introduces significant communication…

Federated learning enables training a global model from data located at the client nodes, without data sharing and moving client data to a centralized server. Performance of federated learning in a multi-access edge computing (MEC) network…

Tabular data stands out as one of the most frequently encountered types in high energy physics. Unlike commonly homogeneous data such as pixelated images, simulating high-dimensional tabular data and accurately capturing their correlations…

Implementing Retrieval-Augmented Generation (RAG) systems is inherently complex, requiring deep understanding of data, use cases, and intricate design decisions. Additionally, evaluating these systems presents significant challenges,…

Federated Continual Learning (FCL) has recently emerged as a crucial research area, as data from distributed clients typically arrives as a stream, requiring sequential learning. This paper explores a more practical and challenging FCL…

By leveraging large clusters of commodity hardware, the Cloud offers great opportunities to optimize the operative costs of software systems, but impacts significantly on the reliability of software applications. The lack of control of…

We present Thinking While Driving, a concurrent routing framework that integrates LLMs into a graph-based traffic environment. Unlike approaches that require agents to stop and deliberate, our system enables LLM-based route planning while…

Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by…

Arising user-centric graph applications such as route planning and personalized social network analysis have initiated a shift of paradigms in modern graph processing systems towards multi-query analysis, i.e., processing multiple graph…

Resource provisioning in multi-tenant stream processing systems faces the dual challenges of keeping resource utilization high (without over-provisioning), and ensuring performance isolation. In our common production use cases, where…

Deploying autonomous vision systems on edge devices faces a critical challenge: resource constraints prevent real-time and predictable execution of comprehensive safety tests. Existing validation methods depend on static datasets or manual…

Knowledge graph embedding, which aims to learn the low-dimensional representations of entities and relationships, has attracted considerable research efforts recently. However, most knowledge graph embedding methods focus on the structural…

Federated learning (FL) has emerged as a powerful approach to safeguard data privacy by training models across distributed edge devices without centralizing local data. Despite advancements in homogeneous data scenarios, maintaining…

The rapid progress of large language models (LLMs) has catalyzed the emergence of multimodal large language models (MLLMs) that unify visual understanding and image generation within a single framework. However, most existing MLLMs rely on…

Graph analytics are vital in fields such as social networks, biomedical research, and graph neural networks (GNNs). However, traditional CPUs and GPUs struggle with the memory bottlenecks caused by large graph datasets and their…

We propose a novel and efficient, custom frame synchronization architecture aimed at rapid deployment on any hardware platform. Frame synchronization is the process of discerning valid data frames from an incoming transmission and in this…

Large Language Model (LLM) inference on edge Neural Processing Units (NPUs) is fundamentally constrained by limited on-chip memory capacity. Although high-density embedded DRAM (eDRAM) is attractive for storing activation workspaces, its…

Subgraph isomorphism is a fundamental problem in graph analysis that seeks to find all instances of a pattern graph within a larger data graph while preserving structural relationships. This NP-complete problem is central to domains such as…