Skip to content
← Implement-from-Scratch Coding / 21
hardNewOpenAIAnthropicBaseten

A streaming client stops reading. Keep its output bounded without blocking the inference batch.

One slow connection can stall unrelated generations or retain an unbounded output queue. Implement a byte budget that includes the pending write, then connect overflow and disconnects to engine cancellation.

Updated Oct 2026 · Worked answers on inference mechanisms, with calculations, implementation details, and follow-up questions.

One slow connection can stall unrelated generations or retain an unbounded output queue. Implement a byte budget that includes the pending write, then connect overflow and disconnects to engine cancellation.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 136 remaining answers · ₹2,000 / $25

Every worked answer and derivation in all 12 topics, every concept page, and the full practice-test bank.

6 months · One payment · No auto-renewal

UP NEXT ON YOUR JOURNEY
Popular right nowWhy is batch-1 decode on a 70B model bandwidth-bound, and what is its latency floor on two H100s?Popular right nowDerive the FLOPs per token for a dense transformer from its config. Where does the 2N rule stop being accurate?Popular right nowWhy does prefill turn compute-bound after a few hundred tokens on an H100, and how long does a 4K-token prompt take on a 70B model?
FEDITOR'S NOTE

Transport completion, client receipt and GPU completion are different events. A correct output buffer cannot prove that KV pages are safe to reuse.

DISCUSSION · 0

Nobody has commented on this answer. Add a correction or another way to work it.