core practice · system design prompt

Design exercise: KV Caching & PagedAttention

Attention-state reuse, KV memory sizing, paging, fragmentation, prefix caching, eviction, and multi-tenant pressure. Implement designOutline() returning non-empty values for: cacheSizing, pageMapping, evictionPolicy. Each value must name a concrete mechanism or decision.

The mechanism

The KV cache trades memory for avoided recomputation. PagedAttention maps logical token blocks to non-contiguous physical pages so variable-length requests waste less memory.

Study KV Caching & PagedAttention

Expected evidence

A design outline with cacheSizing, pageMapping, evictionPolicy plus an explicit failure mode or trade-off.

Try this drill in the practice workspace →

Hints when you need them
  • Name the failure mode before selecting the mechanism.

Check the sources

Browse all practice briefs