Coursera
All levels
Subscription

Model Optimization, Inference & End-to-End Engineering

~10 hours

Production deep learning engineering demands model compression, accelerated inference, and reliable deployment infrastructure on Azure ML. You'll apply post-training quantization (INT8/FP16), quantization-aware training, structured pruning, and knowledge distillation to compress models and benchmark accuracy-latency trade-offs. You'll configure CUDA and TensorRT with ONNX Runtime and Hugging Face Optimum for accelerated inference, then deploy containerized models to Azure ML online and batch endpoints with autoscaling and blue/green deployment patterns. By the end of this course, you'll be a

Skills you'll learn

We may earn a commission if you enroll through our links — it never affects the price you pay.

Similar courses