Related papers: [Extended Version] ArceKV: Towards Workload-driven…
Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from…
With the current rate of data growth, processing needs are becoming difficult to fulfill due to CPU power and energy limitations. Data serving systems and especially persistent key-value stores have become a substantial part of data…
This paper studies the design of B-tree that can take full advantage of modern storage hardware with built-in transparent compression. Recent years have witnessed significant interest in applying log-structured merge tree (LSM-tree) as an…
In this work, we propose D3-Tree, a dynamic distributed deterministic structure for data management in decentralized networks. We present in brief the theoretical algorithmic analysis, in which our proposed structure is based on, and we…
Cloud key-value (KV) stores provide businesses with a cost-effective and adaptive alternative to traditional on-premise data management solutions. KV stores frequently consist of heterogeneous clusters, characterized by varying hardware…
We present Adaptive Soft Rolling KV Freeze with Entropy-Guided Recovery (ASR-KF-EGR), a training-free inference-time framework for efficient large language model generation. Our method introduces a reversible soft-freeze mechanism that…
Decision trees are considered one of the most powerful tools for data classification. Accelerating the decision tree search is crucial for on-the-edge applications that have limited power and latency budget. In this paper, we propose a…
Existing storage systems lack visibility into workload intent, limiting their ability to adapt to the semantics of modern, large-scale data-intensive applications. This disconnect leads to brittle heuristics and fragmented, siloed…
Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…
The Fenwick tree is a classical implicit data structure that stores an array in such a way that modifying an element, accessing an element, computing a prefix sum and performing a predecessor search on prefix sums all take logarithmic time.…
Energy systems optimization problems are complex due to strongly non-linear system behavior and multiple competing objectives, e.g. economic gain vs. environmental impact. Moreover, a large number of input variables and different variable…
Achieving sustainable, explainable, and maintainable automation for resource optimization is a core challenge across the edge-cloud continuum. Persistent overprovisioning and operational complexity often stem from heterogeneous platforms…
Large language models (LLMs) are increasingly deployed in AI infrastructure, driving the need for high throughput, resource efficient serving systems. Disaggregated LLM serving, which separates prompt prefill from auto-regressive decode,…
Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks. Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the…
The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG)…
In order to meet the performance/privacy requirements of future data-intensive mobile applications, e.g., self-driving cars, mobile data analytics, and AR/VR, service providers are expected to draw on shared storage/computation/connectivity…
In open source software development, the reuse of existing artifacts has been widely adopted to avoid redundant implementation work. Reusable artifacts are considered more efficient and reliable than developing software components from…
Mixture-of-Experts (MoE) models promise efficient scaling of large language models (LLMs) by activating only a small subset of experts per token, but their parallelized inference pipelines make elastic serving challenging. Existing…
Our extensive real measurements over Amazon EC2 show that the virtual instances often have different computing speeds even if they share the same configurations. This motivates us to study heterogeneous Coded Storage Elastic Computing…
Large language models (LLMs) have demonstrated impressive capabilities and are receiving increasing attention to enhance their reasoning through scaling test--time compute. However, their application in open--ended, knowledge--intensive,…