/course/index.html/course/llm-basics-1-what-a-model-is-on-disk.html/course/llm-basics-2-tokens-and-embeddings.html/course/llm-basics-3-a-layer-is-matrix-multiplication.html/course/llm-basics-4-the-forward-pass.html/course/llm-basics-5-generating-text.html/course/llm-basics-6-attention-and-the-kv-cache.html/course/llm-basics-7-the-hardware-fit.html/index.html/course/why-llm-decode-is-memory-bound.html