Guided learning path
Model Internals
Connect model execution, token generation, context, and KV-cache behaviour to memory use and serving performance.
Who this path is for
Engineers who want to understand the mechanisms behind inference latency and memory pressure.
What you will learn
Describe prefill and decode; reason about context and KV-cache growth; distinguish cache retention, transfer, and recomputation.
Prerequisites
Basic familiarity with language-model prompts and tokens. Some understanding of arrays and memory sizes is useful.
Difficulty and workload
Intermediate. Read the cache budget article first, sketch its memory model, then examine how a tool call changes the execution lifecycle.
Suggested reading sequence
- The KV Cache Is Your Real LLM Serving Budget
- When an Agent Calls a Tool, What Happens to Its KV Cache?
- When Q4 Passes Latency but Fails Quality
This reading sequence uses existing articles. New guided lessons will appear in the published-lessons list below. Return to all learning paths to explore a related subject.
Curriculum
Published lessons
- No lessons have been published in this path yet.