MASTER ONNX AND BUILD PRODUCTION-READY AI INFERENCE SYSTEMS.
Machine learning does not end with model training. To use an AI model in the real world, you need reliable model conversion, optimized inference, hardware acceleration, scalable deployment, and production monitoring.
PRODUCTION ONNX: Model Conversion, Runtime Optimization, Hardware Acceleration, and AI Deployment is a practical technical guide to ONNX and ONNX Runtime, designed for developers, AI engineers, machine-learning engineers, and MLOps practitioners who want to move models from development into production.
Inside, you’ll learn how to:
Understand ONNX models, tensors, operators, and computational graphs
Convert PyTorch and other machine-learning models to ONNX
Validate and troubleshoot ONNX model conversion
Optimize ONNX graphs and improve AI inference performance
Apply quantization, INT8, FP16, and reduced-precision inference
Accelerate inference with CUDA, NVIDIA GPUs, TensorRT, OpenVINO, DirectML, and other execution providers
Build efficient ONNX Runtime inference pipelines and APIs
Deploy AI inference services using Docker, Kubernetes, and cloud infrastructure
Improve throughput with batching, concurrency, scheduling, and horizontal scaling
Implement monitoring, logging, tracing, metrics, and AI observability
Secure ONNX models, inference APIs, and production deployments
Perform advanced ONNX Runtime performance tuning and optimization
Build cross-platform ONNX deployment and optimization pipelines
Manage model versions, rollouts, rollbacks, testing, and production reliability
Balance inference speed, model accuracy, infrastructure cost, and maintainability
From ONNX model conversion and runtime optimization to GPU acceleration, AI deployment, MLOps, and production inference, this book provides a complete path for turning trained machine-learning models into reliable production systems.
If you want to understand ONNX, ONNX Runtime, model optimization, quantization, hardware acceleration, and scalable AI inference, PRODUCTION ONNX gives you the practical foundation to build and operate modern machine-learning inference systems.
Convert. Optimize. Accelerate. Deploy.
"Sinopsis" puede pertenecer a otra edición de este libro.
Librería: California Books, Miami, FL, Estados Unidos de America
Condición: New. Print on Demand. Nº de ref. del artículo: I-9798171013226
Cantidad disponible: Más de 20 disponibles
Librería: Grand Eagle Retail, Bensenville, IL, Estados Unidos de America
Paperback. Condición: new. Paperback. MASTER ONNX AND BUILD PRODUCTION-READY AI INFERENCE SYSTEMS.Machine learning does not end with model training. To use an AI model in the real world, you need reliable model conversion, optimized inference, hardware acceleration, scalable deployment, and production monitoring.PRODUCTION ONNX: Model Conversion, Runtime Optimization, Hardware Acceleration, and AI Deployment is a practical technical guide to ONNX and ONNX Runtime, designed for developers, AI engineers, machine-learning engineers, and MLOps practitioners who want to move models from development into production.Inside, you'll learn how to: Understand ONNX models, tensors, operators, and computational graphsConvert PyTorch and other machine-learning models to ONNXValidate and troubleshoot ONNX model conversionOptimize ONNX graphs and improve AI inference performanceApply quantization, INT8, FP16, and reduced-precision inferenceAccelerate inference with CUDA, NVIDIA GPUs, TensorRT, OpenVINO, DirectML, and other execution providersBuild efficient ONNX Runtime inference pipelines and APIsDeploy AI inference services using Docker, Kubernetes, and cloud infrastructureImprove throughput with batching, concurrency, scheduling, and horizontal scalingImplement monitoring, logging, tracing, metrics, and AI observabilitySecure ONNX models, inference APIs, and production deploymentsPerform advanced ONNX Runtime performance tuning and optimizationBuild cross-platform ONNX deployment and optimization pipelinesManage model versions, rollouts, rollbacks, testing, and production reliabilityBalance inference speed, model accuracy, infrastructure cost, and maintainabilityFrom ONNX model conversion and runtime optimization to GPU acceleration, AI deployment, MLOps, and production inference, this book provides a complete path for turning trained machine-learning models into reliable production systems.If you want to understand ONNX, ONNX Runtime, model optimization, quantization, hardware acceleration, and scalable AI inference, PRODUCTION ONNX gives you the practical foundation to build and operate modern machine-learning inference systems.Convert. Optimize. Accelerate. Deploy. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability. Nº de ref. del artículo: 9798171013226
Cantidad disponible: 1 disponibles
Librería: PBShop.store UK, Fairford, GLOS, Reino Unido
PAP. Condición: New. New Book. Shipped from UK. Established seller since 2000. Nº de ref. del artículo: L2-9798171013226
Cantidad disponible: Más de 20 disponibles
Librería: CitiRetail, Stevenage, Reino Unido
Paperback. Condición: new. Paperback. MASTER ONNX AND BUILD PRODUCTION-READY AI INFERENCE SYSTEMS.Machine learning does not end with model training. To use an AI model in the real world, you need reliable model conversion, optimized inference, hardware acceleration, scalable deployment, and production monitoring.PRODUCTION ONNX: Model Conversion, Runtime Optimization, Hardware Acceleration, and AI Deployment is a practical technical guide to ONNX and ONNX Runtime, designed for developers, AI engineers, machine-learning engineers, and MLOps practitioners who want to move models from development into production.Inside, you'll learn how to: Understand ONNX models, tensors, operators, and computational graphsConvert PyTorch and other machine-learning models to ONNXValidate and troubleshoot ONNX model conversionOptimize ONNX graphs and improve AI inference performanceApply quantization, INT8, FP16, and reduced-precision inferenceAccelerate inference with CUDA, NVIDIA GPUs, TensorRT, OpenVINO, DirectML, and other execution providersBuild efficient ONNX Runtime inference pipelines and APIsDeploy AI inference services using Docker, Kubernetes, and cloud infrastructureImprove throughput with batching, concurrency, scheduling, and horizontal scalingImplement monitoring, logging, tracing, metrics, and AI observabilitySecure ONNX models, inference APIs, and production deploymentsPerform advanced ONNX Runtime performance tuning and optimizationBuild cross-platform ONNX deployment and optimization pipelinesManage model versions, rollouts, rollbacks, testing, and production reliabilityBalance inference speed, model accuracy, infrastructure cost, and maintainabilityFrom ONNX model conversion and runtime optimization to GPU acceleration, AI deployment, MLOps, and production inference, this book provides a complete path for turning trained machine-learning models into reliable production systems.If you want to understand ONNX, ONNX Runtime, model optimization, quantization, hardware acceleration, and scalable AI inference, PRODUCTION ONNX gives you the practical foundation to build and operate modern machine-learning inference systems.Convert. Optimize. Accelerate. Deploy. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability. Nº de ref. del artículo: 9798171013226
Cantidad disponible: 1 disponibles
Librería: AHA-BUCH GmbH, Einbeck, Alemania
Taschenbuch. Condición: Neu. Neuware. Nº de ref. del artículo: 9798171013226
Cantidad disponible: 2 disponibles