Inference Optimization
Two phases define LLM inference. Prefill processes your prompt in parallel -- compute-bound. Decode generates tokens one at a time -- memory-bound. Every optimization targets one or both.
Visual edition planned
This lesson isn’t interactive yet.
It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:
Part of Phase 10 — LLMs from Scratch. Use the previous / next cards below to keep browsing the phase.