Practice labs
Runnable CPU-only companion labs for Track 1. These are practice material, separate from the published lesson count.
- Lab 01 — Attention and masksImplement single-head and multi-head attention, verify tensor shapes, stable softmax, causal future-token isolation, and numerical parity with PyTorch. Diagnose a causal mask that passes shape checks but leaks future tokens.Open lab
- Lab 02 — Tiny decoder trainingAssemble a tiny decoder, overfit a fixed batch, assert shapes and parameter count, and diagnose a label-shift bug with a diagnostic check and repair.Open lab
- Lab 03 — Cached generation and GQACompare cached and uncached generation, verify one KV append per layer per step, compute raw MHA versus GQA cache bytes, and diagnose a broken cache write.Open lab