Related papers: FOCUS: Boosting Schema-aware Access for KV Stores …

Attention-based models have been a key element of many recent breakthroughs in deep learning. Two key components of Attention are the structure of its input (which consists of keys, values and queries) and the computations by which these…

Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and…

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

Knowledge management systems (KMS) are in high demand for industrial researchers, chemical or research enterprises, or evidence-based decision making. However, existing systems have limitations in categorizing and organizing paper insights…

The data-centric paradigm has emerged as a pivotal direction in artificial intelligence (AI), emphasizing the role of high-quality training data. This shift is especially critical in the Text-to-SQL task, where the scarcity, limited…

In-memory ordered key-value stores are an important building block in modern distributed applications. We present Honeycomb, a hybrid software-hardware system for accelerating read-dominated workloads on ordered key-value stores that…

Visual autoregressive modeling (VAR) via next-scale prediction has emerged as a scalable image generation paradigm. While Key and Value (KV) caching in large language models (LLMs) has been extensively studied, next-scale prediction…

Ubiquitous systems with End-Edge-Cloud architecture are increasingly being used in healthcare applications. Federated Learning (FL) is highly useful for such applications, due to silo effect and privacy preserving. Existing FL approaches…

Real-world vision based applications require fine-grained classification for various area of interest like e-commerce, mobile applications, warehouse management, etc. where reducing the severity of mistakes and improving the classification…

Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…

Zoned storage devices, such as zoned namespace (ZNS) solid-state drives (SSDs) and host-managed shingled magnetic recording (HM-SMR) hard-disk drives (HDDs), expose interfaces for host-level applications to support fine-grained,…

Deployment of Network Function Virtualization (NFV) over multiple clouds accentuates its advantages like the flexibility of virtualization, proximity to customers and lower total cost of operation. However, NFV over multiple clouds has not…

Recent reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical reasoning and code generation. However, this performance gain comes with substantially longer output sequences,…

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the…

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…

Cloud computing has recently emerged as a key technology to provide individuals and companies with access to remote computing and storage infrastructures. In order to achieve highly-available yet high-performing services, cloud data stores…

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

Disaggregated storage systems improve resource utilization and enable independent scaling of storage and compute resources by separating storage resources from computing resources in data centers. NVMe over fabrics (NVMeoF) is a key…

Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV\$) after processing each request substantially improves serving throughput and latency. However, there is limited understanding of…

Vision-Language Models (VLMs) have demonstrated strong performance on tasks such as video captioning and visual question answering. However, their growing scale and video-level inputs lead to significant computational and memory overhead,…