Related papers: Chameleon: a Heterogeneous and Disaggregated Accel…

Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming…

The integration of Retrieval-Augmented Generation (RAG) with Multimodal Large Language Models (MLLMs) has revolutionized information retrieval and expanded the practical applications of AI. However, current systems struggle in accurately…

Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhead, hindering real-world deployment. Accelerating diffusion…

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…

Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer stage with irrelevant context. However, existing memory…

Retrieval-Augmented Generation (RAG) architectures have recently garnered significant attention for their ability to improve truth grounding and coherence in natural language processing tasks. However, the reliability of RAG systems in…

One of the most critical aspects of integrating loosely-coupled accelerators in heterogeneous SoC architectures is orchestrating their interactions with the memory hierarchy, especially in terms of navigating the various cache-coherence…

Large language models demand massive computational power and memory resources, posing significant challenges for efficient deployment. While quantization has been widely explored to reduce model size and computation, this paper demonstrates…

RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has…

Large Language Models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. In this paper, we present a comprehensive survey of…

In hybrid transactional and analytical processing (HTAP) systems, users often struggle to understand why query plans from one engine (OLAP or OLTP) perform significantly slower than those from another. Although optimizers provide plan…

Conventional Retrieval Augmented Generation (RAG) approaches are common in text-based applications. However, they struggle with structured, interconnected datasets like knowledge graphs, where understanding underlying relationships is…

We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using automaton to expedite the reinforcement…

Retrieval-augmented generation (RAG) is a promising method for addressing some of the memory-related challenges associated with Large Language Models (LLMs). Two separate systems form the RAG pipeline, the retriever and the reader, and the…

Large Language Models (LLMs) in agentic workflows combine multi-step reasoning, heterogeneous tool use, and collaboration across multiple specialized agents. Existing LLM serving engines optimize individual calls in isolation, while…

Lane topology extraction involves detecting lanes and traffic elements and determining their relationships, a key perception task for mapless autonomous driving. This task requires complex reasoning, such as determining whether it is…

Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items…

A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge. It also delivers more specialized responses compared to…

Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant…

Large Language Models (LLMs) demand substantial computational resources, resulting in high energy consumption on GPUs. To address this challenge, we focus on Coarse-Grained Reconfigurable Arrays (CGRAs) as an effective alternative that…