Skip to content
← Attention Kernels / 19
hardNewNVIDIATogether AIFireworks AI

What does DSA's lightning indexer plus top-2,048 selection cost at 128K context, and when does it beat dense attention?

Sparse attention still reads a key for every cached token, just a smaller one. The answer prices both passes in bytes and FLOPs, finds the context where sparse starts winning, and names the cost it does not remove.

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

Sparse attention still reads a key for every cached token, just a smaller one. The answer prices both passes in bytes and FLOPs, finds the context where sparse starts winning, and names the cost it does not remove.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 213 remaining answers · $25

Every worked answer and derivation in all 12 topics, every concept page, the full practice-test bank, and every code drill’s edge-case tests and reference solution.

6 months · One payment · No auto-renewal

UP NEXT ON YOUR JOURNEY
Next in this trackSparse MLA decode on a B200 reads FP8 or FP4 KV but multiplies in BF16. Is it bandwidth-bound, and why dequantize?Next in this trackWhich attention kernel will vLLM and SGLang actually run on an H100 and a B200, and what silently changes the answer?Next in this trackResearch hands you document masking plus sink tokens to serve. FlexAttention, or fork a FlashAttention kernel?
DISCUSSION · 0

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