Problems / LLM serving, medium
A self-hosted 70B model runs on 4 GPU replicas that autoscale to 16. At 20 s traffic triples, from 40 to 120 requests a second. Each new replica must load 140 GB of weights before it serves: 60 s here (2–5 minutes in practice).
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.
Success ≥ 99%.
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 3; 1 of them are hidden until then.
40 requests a second for 90 seconds: 100% request (reads).
What each component does in this design, and what calls it. The simulator mimics each one from these settings.
| Component | Its job here | Settings |
|---|---|---|
| Load balancerLoad balancer | Traffic 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 service | Load balancer forwards to it.Calls GPU serving pool (70B).Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 3 replicas × 500 slots · timeout 30 s |
| GPU serving pool (70B)Self-hosted serving pool | AI app calls it.GPU servers batch requests together; throughput rises with batch size until memory runs out. | 12 slots · 4–16 instances |