Problems / LLM serving, medium

Prompt cache that rarely hits

An exact-match prompt cache sits in front of the model but hits only 5%: timestamps in the prompt make every prompt unique. The model’s token quota is tight.

Solve it in the labTake it as a mock interview

Unlock it once for 15 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

Success ≥ 99%, time to first token p99 ≤ 2.5 s.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 6; 2 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. Peak hour. 25% more traffic than the problem states, with the same failures.
  3. A slow dependency. The main data store or model answers twice as slowly for part of the run.
  4. A server dies. One replica of the service with the most replicas is killed for part of the run.

The traffic

45 requests a second for 30 seconds: 100% request (reads).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
Load balancerLoad balancerTraffic enters here.Calls AI app.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
AI appApp serviceLoad balancer forwards to it.Calls Prompt cache.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.3 replicas × 500 slots · timeout 30 s
Prompt cachePrompt cacheAI app calls it.Calls Model.Providers can cache a long repeated prompt prefix, cutting cost and time to first token.2000 slots · 5% hit rate
ModelLLM endpointPrompt cache calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second.400 streams · 4M input tokens/min

More llm serving problems