4 Repos
Infrastructure for launching and serving machine learning models in production.
Distinguishing note: Focuses on production deployment, distinct from model training workflows.
Explore 4 awesome GitHub repositories matching devops & infrastructure · Model Deployment Platforms. Refine with filters or upvote what's useful.
ColossalAI is a distributed deep learning framework designed for training and deploying massive artificial intelligence models across clusters of hardware accelerators. It functions as a parallel computing engine that partitions model workloads and data across multiple processors to maximize memory efficiency and throughput. The platform distinguishes itself through a comprehensive suite of parallelization strategies, including multi-dimensional tensor parallelism and pipeline-based model parallelism, which segment neural network layers and stages across devices. To support large-scale genera
Launches pre-trained or custom generative models into production environments for specialized tasks.
ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,
Integrates exported models into Android, iOS, and desktop applications using platform-specific runtime bindings.
Dieses Projekt ist eine umfassende Bildungsressource und ein Tutorial-Handbuch für das Erstellen, Trainieren und Bereitstellen von Machine-Learning-Modellen mit TensorFlow 2. Es dient als strukturierter Lernleitfaden für grundlegende Deep-Learning-Konzepte, einschließlich neuronaler Netzwerkarchitekturen, automatischer Differenzierung und Tensor-Operationen. Das Handbuch bietet technische Anleitungen zur Optimierung der Ausführungseffizienz durch GPU-Speicherverwaltung, verteiltes Training und Modellquantisierung. Es enthält zudem detaillierte Anleitungen für den Aufbau leistungsfähiger Datenpipelines und den Export von Modellen für Produktionsserver, mobile Geräte und Webbrowser. Das Material deckt ein breites Spektrum an Funktionen ab, darunter die Modellentwicklung mit konvolutionellen und rekurrenten Netzwerken, die Implementierung benutzerdefinierter Verlustfunktionen und Layer sowie die Nutzung vortrainierter Modelle für Transfer Learning. Zudem werden Bereitstellungsstrategien für Edge-Geräte und die Nutzung cloudbasierter Runtimes zur Hardwarebeschleunigung behandelt. Die Ressource ist als Sammlung von Jupyter Notebooks implementiert.
Provides detailed manuals for exporting trained models for production servers, mobile devices, and web browsers.
This project is a machine learning interoperability tool designed to translate models from various training frameworks into the standardized open neural network exchange format. It functions as a model deployment pipeline that enables consistent execution across diverse inference engines and hardware environments. The tool utilizes graph-based translation and an operator mapping layer to convert framework-specific mathematical functions into a common intermediate representation. It distinguishes itself through a pluggable converter architecture, which allows developers to register custom tran
Facilitates moving models from research environments into production by standardizing formats for diverse hardware targets.