Emerging Platforms Meet Emerging LLMs: A Year-Long Journey of Top-Down Development

• URL: http://arxiv.org/abs/2404.09151v2
• Date: Tue, 16 Apr 2024 09:29:02 GMT
• Title: Emerging Platforms Meet Emerging LLMs: A Year-Long Journey of Top-Down Development
• Authors: Siyuan Feng, Jiawei Liu, Ruihang Lai, Charlie F. Ruan, Yong Yu, Lingming Zhang, Tianqi Chen,
• Abstract summary: We introduce TapML, a top-down approach and tooling designed to streamline the deployment of machine learning systems on diverse platforms. Unlike traditional bottom-up methods, TapML automates unit testing and adopts a migration-based strategy for gradually offloading model computations. TapML was developed and applied through a year-long, real-world effort that successfully deployed significant emerging models and platforms.
• Score: 20.873143073842705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying machine learning (ML) on diverse computing platforms is crucial to accelerate and broaden their applications. However, it presents significant software engineering challenges due to the fast evolution of models, especially the recent Large Language Models (LLMs), and the emergence of new computing platforms. Current ML frameworks are primarily engineered for CPU and CUDA platforms, leaving a big gap in enabling emerging ones like Metal, Vulkan, and WebGPU. While a traditional bottom-up development pipeline fails to close the gap timely, we introduce TapML, a top-down approach and tooling designed to streamline the deployment of ML systems on diverse platforms, optimized for developer productivity. Unlike traditional bottom-up methods, which involve extensive manual testing and debugging, TapML automates unit testing through test carving and adopts a migration-based strategy for gradually offloading model computations from mature source platforms to emerging target platforms. By leveraging realistic inputs and remote connections for gradual target offloading, TapML accelerates the validation and minimizes debugging scopes, significantly optimizing development efforts. TapML was developed and applied through a year-long, real-world effort that successfully deployed significant emerging models and platforms. Through serious deployments of 82 emerging models in 17 distinct architectures across 5 emerging platforms, we showcase the effectiveness of TapML in enhancing developer productivity while ensuring model reliability and efficiency. Furthermore, we summarize comprehensive case studies from our real-world development, offering best practices for developing emerging ML systems.

Related papers

• LLM-enabled Instance Model Generation [4.52634430160579]
  This work explores the generation of instance models using large language models (LLMs) We propose a two-step approach: first, using LLMs to produce a simplified structured output containing all necessary instance model information, and then compiling this intermediate representation into a valid XMI file. Results show that the proposed method significantly improves the usability of LLMs for instance model generation tasks.
  arXiv  Detail & Related papers  (2025-03-28T16:34:29Z)
• PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing [48.30406812516552]
  We introduce the PLM, a Peripheral Language Model, developed through a co-design process that jointly optimize model architecture and edge system constraints. PLM employs a Multi-head Latent Attention mechanism and employs the squared ReLU activation function to encourage sparsity, thereby reducing peak memory footprint. evaluation results demonstrate that PLM outperforms existing small language models trained on publicly available data.
  arXiv  Detail & Related papers  (2025-03-15T15:11:17Z)
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling [128.24325909395188]
  We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0. InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems.
  arXiv  Detail & Related papers  (2024-12-06T18:57:08Z)
• AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment [13.977849745488339]
  AmoebaLLM is a novel framework designed to enable the instant derivation of large language models of arbitrary shapes. AmoebaLLM significantly facilitates rapid deployment tailored to various platforms and applications.
  arXiv  Detail & Related papers  (2024-11-15T22:02:28Z)
• Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance [78.48606021719206]
  Mini-InternVL is a series of MLLMs with parameters ranging from 1B to 4B, which achieves 90% of the performance with only 5% of the parameters. We develop a unified adaptation framework for Mini-InternVL, which enables our models to transfer and outperform specialized models in downstream tasks.
  arXiv  Detail & Related papers  (2024-10-21T17:58:20Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs [36.409470894115074]
  We propose the CodePLAN framework, which aims to transfer LLMs' code generation reasoning capabilities to smaller models. Our approach improves the smaller model's code generation performance by over 130% on the challenging APPS benchmark.
  arXiv  Detail & Related papers  (2024-03-20T03:09:54Z)
• Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning [79.53130089003986]
  Large Language Models (LLMs) have become a feasible solution for handling tasks in various domains. In this paper, we introduce how to fine-tune a LLM model that can be privately deployed for content moderation.
  arXiv  Detail & Related papers  (2023-10-05T09:09:44Z)
• Model Share AI: An Integrated Toolkit for Collaborative Machine Learning Model Development, Provenance Tracking, and Deployment in Python [0.0]
  We introduce Model Share AI (AIMS), an easy-to-use MLOps platform designed to streamline collaborative model development, model provenance tracking, and model deployment. AIMS features collaborative project spaces and a standardized model evaluation process that ranks model submissions based on their performance on unseen evaluation data. AIMS allows users to deploy ML models built in Scikit-Learn, Keras, PyTorch, and ONNX into live REST APIs and automatically generated web apps.
  arXiv  Detail & Related papers  (2023-09-27T15:24:39Z)
• MLOps: A Step Forward to Enterprise Machine Learning [0.0]
  This research presents a detailed review of MLOps, its benefits, difficulties, evolutions, and important underlying technologies. The MLOps workflow is explained in detail along with the various tools necessary for both model and data exploration and deployment. This article also puts light on the end-to-end production of ML projects using various maturity levels of automated pipelines.
  arXiv  Detail & Related papers  (2023-05-27T20:44:14Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• Speculative Decoding with Big Little Decoder [108.95187338417541]
  Big Little Decoder (BiLD) is a framework that can improve inference efficiency and latency for a wide range of text generation applications. On an NVIDIA T4 GPU, our framework achieves a speedup of up to 2.12x speedup with minimal generation quality degradation. Our framework is fully plug-and-play and can be applied without any modifications in the training process or model architecture.
  arXiv  Detail & Related papers  (2023-02-15T18:55:29Z)
• SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT [9.477629856092218]
  This paper presents a framework called Semantic Low-Code Engineering for ML Applications (SeLoC-ML) SeLoC-ML enables non-experts to model, discover, reuse, and matchmake ML models and devices at scale. Developers can benefit from semantic application templates, called recipes, to fast prototype end-user applications.
  arXiv  Detail & Related papers  (2022-07-18T13:06:21Z)
• YMIR: A Rapid Data-centric Development Platform for Vision Applications [82.67319997259622]
  This paper introduces an open source platform for rapid development of computer vision applications. The platform puts the efficient data development at the center of the machine learning development process.
  arXiv  Detail & Related papers  (2021-11-19T05:02:55Z)
• ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systems [21.37434583546624]
  This paper implements a lightweight MLOps plugin, termed ModelCI-e (continuous integration and evolution), to address the issue. ModelCI-e embraces continual learning (CL) and ML deployment techniques, providing end-to-end supports for model updating and validation. Preliminary results demonstrate the usability of ModelCI-e, and indicate that eliminating the interference between model updating and inference workloads is crucial for higher system efficiency.
  arXiv  Detail & Related papers  (2021-06-06T13:28:51Z)
• Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale [11.121380180647769]
  We share in this paper our search strategies to adapt reference recommendation models to low-precision hardware. We also discuss the design and development of tool chain so as to maintain our models' accuracy throughout their lifespan. We believe these lessons from the trenches promote better co-design between hardware architecture and software engineering.
  arXiv  Detail & Related papers  (2021-05-26T16:42:33Z)
• Technology Readiness Levels for Machine Learning Systems [107.56979560568232]
  Development and deployment of machine learning systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. We have developed a proven systems engineering approach for machine learning development and deployment. Our "Machine Learning Technology Readiness Levels" framework defines a principled process to ensure robust, reliable, and responsible systems.
  arXiv  Detail & Related papers  (2021-01-11T15:54:48Z)
• Quantitatively Assessing the Benefits of Model-driven Development in Agent-based Modeling and Simulation [80.49040344355431]
  This paper compares the use of MDD and ABMS platforms in terms of effort and developer mistakes. The obtained results show that MDD4ABMS requires less effort to develop simulations with similar (sometimes better) design quality than NetLogo.
  arXiv  Detail & Related papers  (2020-06-15T23:29:04Z)
• MLModelCI: An Automatic Cloud Platform for Efficient MLaaS [15.029094196394862]
  We release the platform as an open-source project on GitHub under Apache 2.0 license. Our system bridges the gap between current ML training and serving systems and thus free developers from manual and tedious work often associated with service deployment.
  arXiv  Detail & Related papers  (2020-06-09T07:48:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.