EasyDeepLearn

What is the KV cache and why does it matter for LLM inference?

hard

Answer

  • During autoregressive generation, attention needs the Keys and Values of all previous tokens.
  • Recomputing them at every step is wasteful, so we cache them and only compute K/V for the new token.
  • Effect: per-token generation becomes O(n) instead of O(n2)O(n^{2}).
  • Downside: memory grows with context length — the KV cache often dominates VRAM usage in long-context inference.
Check yourself — multiple choice
  • The KV cache stores gradients for backprop
  • The KV cache stores past Keys and Values so we don't recompute them
  • The KV cache is only used during training
  • The KV cache is independent of context length

Caching K/V of past tokens makes decoding much faster.

#kv-cache#inference

Practise LLMs & GenAI

214 interview questions in this topic.

Related questions