Назад в каталог
Курс от Red Hat
courseraIT и технологии
Red Hat AI Inference Technical Overview
Курс от Red HatО курсе
Gain essential insights into AI deployment with this Red Hat AI Inference technical overview. Learn how to address the complexities and costs of running AI models in production. Discover how Red Hat's solution, powered by vLLM, optimizes performance and delivers significant cost savings across cloud, on-premise, virtualized, and edge environments. Dive into advanced techniques like quantization and speculative decoding to enhance your AI inference capabilities. This course demonstrates seamless model deployment and management within OpenShift AI, showcasing how you can achieve unparalleled efficiency and flexibility for your AI workloads.
Навыки, которые вы освоите
Model OptimizationAI WorkflowsAI EnablementEnterprise ArchitectureData ScienceDevops ToolsModel DeploymentHugging FaceGenerative Model ArchitecturesModel TrainingPerformance TuningLLM ApplicationCloud DeploymentApplication DeploymentModel EvaluationOpenShiftVirtualizationArtificial Intelligence and Machine Learning (AI/ML)Large Language ModelingToken Optimization
Программа курса
7 модулей · 15 учебных материалов
01Foundations of Enterprise Inference and Operational Challenges4 материалов
02Inference Runtime Ecosystem and Model Compression
Учитесь у экспертов
Red Hat Training
Преподаватель курса