Contents Part 3 · vLLM in depth
Part 3 · vLLM in depth
Loading a model the way you meant: precision, versions, tokenizers, remote code and chat templates
The settings that decide which files vLLM loads and how a conversation becomes the model's prompt, each one run and checked.
Code zip with this lesson
This lesson is part of the paid Inference Engineering course
The founding price is ₹2,222 or $99$49, one payment. It rises to ₹9,999 or $249 after the founding period, and buying now gives you every part as it is released, at no extra cost, with lifetime access.
Free to study first: Introduction: what this course builds, Before you start, Prefill and decode and The KV cache.
Already bought it? Sign in to read this lesson.