expertNewGoogle DeepMindAnthropicMeta

Design attention for a 1M-token context on one 8-GPU node: the kernel, the parallelism across GPUs, and the memory plan.

At 1M tokens a 70B GQA model needs 320 GiB of KV per request and spends over 90% of prefill FLOPs in attention. The answer lays out a plan that fits on eight H100s, then shows which single change to the model breaks it and what replaces it.

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

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

Next in this trackA decode-attention kernel wins at 128K context. What evidence would justify enabling it for other shapes?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?

DISCUSSION · 0

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