Courses
Each course is a complete path with animated diagrams, interactive tools and hands-on labs. The first lessons of every course are free.
Run models on your own hardware
Local LLM InferenceHardware sizing, quantization, runtimes, performance tuning, serving basics, edge and applications. The complete path from “what is a token” to a tuned local setup.
9 tracks · 41 lessons · 19 free · 15 animated diagrams · 3 labs
From one working model to a reliable service
Serving AI in ProductionWhat changes when real users depend on your model: service levels, capacity and cost planning, gateways, autoscaling, observability, safe rollouts and failure handling.
6 tracks · 36 lessons · 8 free · 3 animated diagrams · 4 labs
Build LLM apps that are hard to abuse
AI Security and PrivacyThe threat model for LLM applications, prompt injection, data leakage, tool abuse, privacy engineering and compliance basics, with a hands-on red-team lab.
2 tracks · 12 lessons · 4 free · 3 animated diagrams · 1 labs
Know whether your AI actually works
LLM Evaluation and TestingReplace vibes with evidence: golden datasets, metrics, statistics, LLM-as-judge, RAG and agent testing, regression suites in CI and production monitoring.
2 tracks · 12 lessons · 4 free · 4 animated diagrams · 1 labs
Why inference is fast or slow, and how to make it faster
Inference EngineeringBottleneck maths, attention and GPU architecture, the software stack, engines compared from the inside, and the techniques that matter: quantisation, speculative decoding, parallelism, caching and disaggregation. Ends with a benchmarking capstone.
4 tracks · 12 lessons · 1 free · 0 animated diagrams · 1 labs
Tokenizer to trained transformer, with code you run
Build an LLM from ScratchWrite a BPE tokenizer, attention, a GPT block, a training loop and a sampler in plain Python first, then see how the same ideas map to PyTorch and to modern upgrades like RoPE, RMSNorm, SwiGLU and grouped-query attention.
4 tracks · 10 lessons · 1 free · 0 animated diagrams · 1 labs
Measure, scale and train reasoning step by step
Build a Reasoning ModelWhat reasoning means and how to verify it, chain of thought, self-consistency, search, verifier loops, reinforcement learning with verifiable rewards (a GRPO-style method), distillation and honest evaluation, with runnable toy experiments.
3 tracks · 7 lessons · 1 free · 0 animated diagrams · 1 labs
A tiny llama.cpp, written by you
Build an Inference EngineImplement a complete forward pass, KV cache, sampling, quantised matrix multiplication, batching and an OpenAI-compatible server, first in readable Python and then with the C++ ideas that make it fast.
2 tracks · 7 lessons · 1 free · 0 animated diagrams · 1 labs
Vision, speech, embeddings and images
Multimodal InferenceHow vision-language models, embedding and reranking services, speech recognition, text-to-speech, real-time voice pipelines and diffusion models run, what they cost and how to serve each.
1 tracks · 5 lessons · 1 free · 0 animated diagrams · 0 labs
Adapt a model without wrecking it
Fine-tuning and CustomisationWhen to fine-tune, data preparation, LoRA and QLoRA mathematics, preference tuning, distillation, merging, evaluating a fine-tune and serving adapters, with a runnable LoRA demonstration.
1 tracks · 4 lessons · 1 free · 0 animated diagrams · 0 labs