Open source

Walkthroughs of the open source repositories worth knowing well: what each project does, how to use it, and how to actually read the code, starting from the entry points and following the main path through the modules that matter. Reading a great codebase is the fastest way to absorb its ideas, and each walkthrough is written to be the map I wish I had on a first visit.

Featured walkthrough

vLLM: reading the engine behind fast LLM serving

How to use vLLM in five minutes, the two ideas that make it fast, PagedAttention and continuous batching, and a guided path through the repository from the entry points to the scheduler and the CUDA kernels.

Read the walkthrough →

LLM inference and serving

The engines that turn a checkpoint into tokens per second. These walkthroughs pair with the LLM serving platform design write-up.

Training and modeling

The frameworks models are built and trained in, and the repos that defined how transformer code is written.

Distributed training and scaling

The systems that spread one model across many GPUs and many machines. These pair with the language model from scratch and parallel computing coursework.

Post-training, fine-tuning, and RLHF

Turning a pretrained checkpoint into an instruction-following, aligned, or reasoning model. These pair with the deep reinforcement learning and applied generative AI coursework.

GPU kernels and architectures

Where the FLOPs actually come from, and the sequence architectures reaching past attention.

Agents and autonomous research

Language models wired into loops that plan, use tools, and act, including agents that run their own research.

Diffusion and generative media

The libraries behind image, video, and audio generation.

Retrieval, embeddings, and RAG

Giving a model the right context, through embeddings, vector retrieval, and the data frameworks around them.

Databases and storage

The storage engines most software stands on, and some of the most readable systems code ever published.

Search and data

How things are found and how columns move: the indexing and analytics engines behind retrieval systems like the ones in the systems section.

Web and infrastructure

The servers and frameworks between a request and an answer.