Atlas

Inference Optimization

Batching & Serving

Continuous batching, PagedAttention, and throughput economics.

You can jump straight in, but this star assumes The KV Cache. Not recommended as a first stop.

Four layers of depth

Each layer ends with a quiz. Finish layer 4 and you own this concept.

  1. L1IntuitionWhy serving an LLM to many users at once is a completely different problem than running one prompt.5m
    40 XP
  2. L2MechanicsThe mechanics of continuous batching, paged KV cache memory, and the prefill/decode split.8m
    70 XP
  3. L3CodeImplement a toy continuous-batching scheduler and see how a paged KV cache allocator works.12m
    110 XP
  4. L4FoundationsThe roofline model, arithmetic intensity, and why decode throughput has a hard memory-bandwidth ceiling.15m
    180 XP

33 stars in the atlas.