paper-with-me

Papers

Efficient Unified Caching for Accelerating Heterogeneous AI Workloads

2025-06-14 · Tianze Wang, Yifei Liu, Chen Chen, Pengfei Zuo, Jiawei Zhang, Qizhen Weng, Yin Chen, Zhenhua Han, Jieru Zhao, Quan Chen, Minyi Guo

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access. To avoid code-intrusion complexity and minimize cache space wastage, it is desirable to maintain a unified cache shared by all the workloads. However, existing cache management strategies, designed for specific workloads, struggle to handle the heterogeneous AI workloads in a cluster -- which usually exhibit heterogeneous access patterns and item storage granularities. In this paper, we propose IGTCache, a unified, high-efficacy cache for modern AI clusters. IGTCache leverages a hierarchical access abstraction, AccessStreamTree, to organize the recent data accesses in a tree structure, facilitating access pattern detection at various granularities. Using this abstraction, IGTCache applies hypothesis testing to categorize data access patterns as sequential, random, or skewed. Based on these detected access patterns and granularities, IGTCache tailors optimal cache management strategies including prefetching, eviction, and space allocation accordingly. Experimental results show that IGTCache increases the cache hit ratio by 55.6% over state-of-the-art caching frameworks, reducing the overall job completion time by 52.2%.

📄 PDF Abstract BibTeX arXiv:2506.12370

Code (0)

등록된 구현이 없습니다.

Tasks

Management

Similar Papers 제목 키워드 기반

ToolCaching: Towards Efficient Caching for LLM Tool-calling

2026-01-20 · Yi Zhai, Dian Shen, Junzhou Luo, Bin Yang arxiv

Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with t…

Recency/Frequency Adaptive KV Caching for Large Language Model Serving

2026-06-19 · Yang Shen, Meghana Madhyastha, Robert Underwood, Bogdan Nicolae 외 arxiv

Key-value (KV) caching is a powerful technique for accelerating large language model inference and generation. Inference workloads are large and diverse, which makes them difficult to cache effectively. Existing cache ma…

Question Answering

Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers

2026-03-05 · Guandong Li arxiv

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing …

Video Generation

Atrapos: Real-time Evaluation of Metapath Query Workloads

2022-01-11 · Serafeim Chatzopoulos, Thanasis Vergoulis, Dimitrios Skoutas, Theodore Dalamagas 외

Heterogeneous information networks (HINs) represent different types of entities and relationships between them. Exploring, analysing, and extracting knowledge from such networks relies on metapath queries that identify p…

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

2026-08-18 · Jinshan Liu, Haoran Qin, Xiaobing Tu, Jiacheng Liu 외 arxiv

Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical deployment. Feature caching has emerged a…

Video Generation