# DLHub: Model and Data Serving for Science

arXiv: https://arxiv.org/abs/1811.11213 · HTML: https://mlsanity.com/paper/1811.11213/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 17 of 17)

- [S3: Increasing GPU Utilization during Generative Inference for Higher Throughput](https://mlsanity.com/paper/2306.06000/) (2023)
- [Distributed Deep Learning in Open Collaborations](https://mlsanity.com/paper/2106.10207/) (2021)
- [Applications of physics informed neural operators](https://mlsanity.com/paper/2203.12634/) (2022)
- [KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks](https://mlsanity.com/paper/2107.01739/) (2021)
- [The Pipeline for the Continuous Development of Artificial Intelligence Models -- Current State of Research and Practice](https://mlsanity.com/paper/2301.09001/) (2023)
- [FAIR for AI: An interdisciplinary and international community building perspective](https://mlsanity.com/paper/2210.08973/) (2022)
- [Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources](https://mlsanity.com/paper/2105.06479/) (2021)
- [FAIR principles for AI models with a practical application for accelerated high energy diffraction microscopy](https://mlsanity.com/paper/2207.00611/) (2022)
- [Inference-optimized AI and high performance computing for gravitational wave detection at scale](https://mlsanity.com/paper/2201.11133/) (2022)
- [Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision](https://mlsanity.com/paper/2402.03480/) (2024)
- [Globus Automation Services: Research process automation across the space-time continuum](https://mlsanity.com/paper/2208.09513/) (2022)
- [FAIR AI Models in High Energy Physics](https://mlsanity.com/paper/2212.05081/) (2022)
- [AICCA: AI-driven Cloud Classification Atlas](https://mlsanity.com/paper/2209.15096/) (2022)
- [End-to-end AI framework for interpretable prediction of molecular and crystal properties](https://mlsanity.com/paper/2212.11317/) (2022)
- [RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances](https://mlsanity.com/paper/2207.11434/) (2022)
- [Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs](https://mlsanity.com/paper/2110.08244/) (2021)
- [HMI: Hierarchical Knowledge Management for Efficient Multi-Tenant Inference in Pretrained Language Models](https://mlsanity.com/paper/2504.17449/) (2025)

## Abstract (arXiv)

While the Machine Learning (ML) landscape is evolving rapidly, there has been a relative lag in the development of the "learning systems" needed to enable broad adoption. Furthermore, few such systems are designed to support the specialized requirements of scientific ML. Here we present the Data and Learning Hub for science (DLHub), a multi-tenant system that provides both model repository and serving capabilities with a focus on science applications. DLHub addresses two significant shortcomings in current systems. First, its selfservice model repository allows users to share, publish, verify, reproduce, and reuse models, and addresses concerns related to model reproducibility by packaging and distributing models and all constituent components. Second, it implements scalable and low-latency serving capabilities that can leverage parallel and distributed computing resources to democratize access to published models through a simple web interface. Unlike other model serving frameworks, DLHub can store and serve any Python 3-compatible model or processing function, plus multiple-function pipelines. We show that relative to other model serving systems including TensorFlow Serving, SageMaker, and Clipper, DLHub provides greater capabilities, comparable performance without memoization and batching, and significantly better performance when the latter two techniques can be employed. We also describe early uses of DLHub for scientific applications.