Related papers: MetaHive: A Cache-Optimized Metadata Management fo…

In-memory key-value datastores have become indispensable building blocks of modern cloud-native infrastructures, yet their evolution faces scalability, compatibility, and sustainability constraints. The current literature lacks an…

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Data warehousing is continuously gaining importance as organizations are realizing the benefits of decision oriented data bases. However, the stumbling block to this rapid development is data quality issues at various stages of data…

Edge computing moves the computation closer to the data and the data closer to the user to overcome the high latency communication of cloud computing. Storage at the edge allows data access with high speeds that enable latency-sensitive…

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…

The integration of visual information into Large Language Models (LLMs) has enabled Multimodal LLMs (MLLMs), but the quadratic memory and computational costs of Transformer architectures remain a bottleneck. Existing KV cache eviction…

Distributed storage architectures are foundational to modern cloud-native infrastructure, yet a critical operational bottleneck persists within disaster recovery (DR) workflows: the dependence on content-based cryptographic hashing for data…

As machine learning (ML) models become increasingly deployed through cloud infrastructures, the confidentiality of user data during inference poses a significant security challenge. Homomorphic Encryption (HE) has emerged as a compelling…

Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important…

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression…

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,…

With the ever-growing availability of so-called complex data, especially on the Web, decision-support systems such as data warehouses must store and process data that are not only numerical or symbolic. Warehousing and analyzing such data…

Modern large-scale services such as search engines, messaging platforms, and serverless functions, rely on key-value (KV) stores to maintain high performance at scale. When such services are deployed in constrained memory environments, they…

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…

This paper introduces MadaKV, a modality-adaptive key-value (KV) cache eviction strategy designed to enhance the efficiency of multimodal large language models (MLLMs) in long-context inference. In multimodal scenarios, attention heads…

Heterogeneous Multi-Embodied Agent Systems involve coordinating multiple embodied agents with diverse capabilities to accomplish tasks in dynamic environments. This process requires the collection, generation, and consumption of massive,…

Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversaries infer sensitive user inputs from shared entries, leading…

In large-scale distributed file systems, efficient meta- data operations are critical since most file operations have to interact with metadata servers first. In existing distributed hash table (DHT) based metadata management systems, the…

Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important…

The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when they process long contexts. Current KV Cache eviction has become an important research…