10k+ learners27+ countries
Trusted by engineers from
Start with how a model produces tokens, then operate each serving engine. Every course ends with a final quiz and an optional project.
Learn how a language model turns a prompt into a streamed answer, and what each step costs in memory and time. Work through real numbers for Llama 3.1 8B, runnable NumPy code, and the measurements serving teams rely on.
Learn to run vLLM 0.28.0 in production: serve models from Python and an OpenAI-compatible API, see how its scheduler and paged KV cache work inside, and tune caching, structured output, quantization, and multi-GPU serving with measurements.
Run SGLang in production. Serve models over HTTP and Python, reuse shared prompt prefixes with the radix cache, constrain output and parse tool calls, scale across GPUs, and benchmark every change with evidence you can defend.
Run a fleet of inference engines as one service with NVIDIA Dynamo. Put one frontend in front of many vLLM or SGLang workers, route each request to the worker that already holds its KV cache, split prefill and decode across GPUs, deploy and scale on Kubernetes, and keep serving when workers fail.
Framework courses for the model code the serving engines run.
Learn PyTorch from the first tensor to a model you can hand over. Build and train models with autograd, modules, data loaders, and optimizers, evaluate them without leakage, save and restore them safely, and make inference faster with batching, mixed precision, compilation, and export, proving every change with a measurement.
Learn to load, run, adapt, and ship pretrained models with Hugging Face Transformers. Pin checkpoints to exact revisions, turn text, images, and audio into model inputs, read logits and generate text, fine-tune with Trainer and LoRA, and package a model that a serving engine such as vLLM can load, checking each step against a known answer.
Implement inference kernels and algorithms in Python, then run hidden tests in your browser.
Open practiceCheck which engines, versions, hardware, and quantization formats support a model.
Search the directory
