Related papers: Samyama: A Unified Graph-Vector Database with In-D…

Graphs are widely used for modeling relational data in real-world scenarios, such as social networks and urban computing. Existing LLM-based graph analysis approaches either integrate graph neural networks (GNNs) for specific machine…

Graph combinatorial optimization (GCO) problems are central to domains like logistics and bioinformatics. While traditional solvers dominate, large language models (LLMs) offer new possibilities for structured reasoning, yet struggle with…

Retrieval-augmented generation (RAG) has emerged as one of the most prominent applications of vector databases. By integrating documents retrieved from a database into the prompt of a large language model (LLM), RAG enables more reliable…

Large Language Model (LLM)-based agents demonstrate strong reasoning and execution capabilities on complex tasks when guided by structured instructions, commonly referred to as workflows. However, existing workflow-assisted agent serving…

We propose LIGHTNE 2.0, a cost-effective, scalable, automated, and high-quality network embedding system that scales to graphs with hundreds of billions of edges on a single machine. In contrast to the mainstream belief that distributed…

Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE…

Weight-only quantization has been widely explored in large language models (LLMs) to reduce memory storage and data loading overhead. During deployment on single-instruction-multiple-threads (SIMT) architectures, weights are stored in…

Modern RISC vector processors rely on the synergy of multi-lane parallelism and chaining to achieve high sustained throughput, yet their achieved performance often falls substantially short of the theoretical performance bound due to…

To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core…

Graph Neural Networks (GNNs) are becoming a promising technique in various domains due to their excellent capabilities in modeling non-Euclidean data. Although a spectrum of accelerators has been proposed to accelerate the inference of…

Vision-Language Models (VLMs) have emerged as versatile solutions for zero-shot question answering (QA) across various domains. However, enabling VLMs to effectively comprehend structured graphs and perform accurate, efficient QA remains…

Driving scenario data play an increasingly vital role in the development of intelligent vehicles and autonomous driving. Accurate and efficient scenario data search is critical for both online vehicle decision-making and planning, and…

The research interest in specialized hardware accelerators for deep neural networks (DNN) spikes recently owing to their superior performance and efficiency. However, today's DNN accelerators primarily focus on accelerating specific…

Improving single-thread performance remains a critical challenge in modern processor design, as conventional approaches such as deeper speculation, wider pipelines, and complex out-of-order execution face diminishing returns. This work…

Data analytics systems commonly utilize in-memory query processing techniques to achieve better throughput and lower latency. Modern computers increasingly rely on Non-Uniform Memory Access (NUMA) architectures in order to achieve…

Graph-centric cross-model data integration and analytics (GCDIA) refer to tasks that leverage the graph model as a central paradigm to integrate relevant information across heterogeneous data models, such as relational and document, and…

Range minimum queries are frequently used in string processing and database applications including biological sequence analysis, document retrieval, and web search. Hence, various data structures have been proposed for improving their…

While Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge, conventional single-agent RAG remains fundamentally limited in resolving complex queries demanding coordinated reasoning across…

This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic…

Designing accelerators for resource- and power-constrained applications is a daunting task. High-level Synthesis (HLS) addresses these constraints through resource sharing, an optimization at the HLS binding stage that maps multiple…