mediumNewOpenAIBaseten

You stream tokens to clients over HTTP. What can go wrong, and how does the server handle each case?

A stream is a long-lived connection to a GPU slot. Slow readers, dropped connections, half-finished answers and duplicate retries each waste that slot in a different way, and each has a specific defense.

Updated Sep 2026 · Grounded in real AI infrastructure interview loops and written to a senior-engineer editorial bar, with every number worked and every diagram hand-built.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 283 remaining answers · ₹2,000 / $25

The concepts behind this question

Ranked by how closely each one overlaps this question's topic, so the first card is the thing to read if the answer above moved too fast.

Core

💻 Coding for InfraSign in

Retry, Backoff and IdempotencyA retry is a second request that the system did not budget for, and a thousand clients retrying at the same moment is a second outage that the first one caused. The craft is small and specific: retry only what is safe to retry, wait an exponentially growing random interval so the retries spread out, cap the total retries with a budget, and make every retried operation idempotent so a duplicate does not double-charge or double-train. This page derives why synchronized retries double the load, works the jitter arithmetic, implements the client correctly, and covers idempotency keys for the operations an AI platform exposes.

Foundational

📐 AI Systems Design

Control Plane and API Design for GPU PlatformsEvery GPU platform has a control plane, and its API is what the rest of the organization experiences as the platform. Three semantics decide whether it survives contact with a network: idempotent creation so a retried request does not launch a second job on sixty-four GPUs, cancellation modelled as intent because only the node agent can stop a running process, and cursor pagination that does not skip rows when work is created during a listing.

Advanced

💻 Coding for Infra🔒 Premium

Batching Queues and BackpressureWrite a request batcher is the coding round's version of the serving engine's scheduler: requests arrive one at a time, the GPU wants them in groups, and the batcher decides when a group is full enough to send without holding anyone too long or accepting more than it can hold. The two knobs are the maximum batch size and the maximum wait, the invariant is a bounded queue, and the follow-ups (priorities, cost-aware batching, cancellation, bounded in-flight batches) are the ideas the real engines carry. This page implements the batcher in asyncio, derives what each knob buys, and walks the follow-ups.

Advanced

📐 AI Systems Design🔒 Premium

Capacity and BackpressureA system that accepts more work than it can finish does not degrade gracefully; it degrades completely, because every request it queues makes every other request slower until all of them time out. The defence is backpressure: bounded queues at every stage, admission control that rejects early when the expected wait exceeds the budget, load shedding by priority, and clients that back off. For LLM serving the stages are the gateway, the router, the engine's queue and its KV pool. This page works the arithmetic of why unbounded queues kill p99, designs the bounds per stage, and the client contract that keeps it stable under overload.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackYou need to serve 128k-token contexts. What breaks first, and what do you change?Next in this trackEAGLE, Medusa or a separate draft model: which speculative decoding method do you pick, and why?Next in this trackDraw the throughput versus latency curve for LLM serving and explain where you would operate on it.

FEDITOR'S NOTE

Scored on connecting client-side failures to the GPU resource they waste, on the cancellation path through the engine, and on idempotent retries that do not double-bill or double-generate.

DISCUSSION · 0

No comments yet — be the first to share your approach.