Field note 08 · May 2026 · builder

Subquadratic sparse attention finally shipped

  • sparse-attention
  • nsa
  • dsa
  • ssa
  • long-context
  • deepseek-v3.2-exp
  • subquadratic
  • lightning-indexer
3-architecture comparison card
3-architecture comparison card

Your next long-context model probably won't run quadratic attention.

For five years, subquadratic attention was a research artifact. In 2025 it shipped.

Three architectures to know:

NSA — Native Sparse Attention (DeepSeek, ACL 2025 best paper) Three parallel paths per query: compressed coarse-grained tokens, selectively retained fine-grained tokens, and a sliding window. Hardware-aligned. Trainable end-to-end — not bolted on after pretraining.

DSA — DeepSeek Sparse Attention (DeepSeek-V3.2-Exp, 2025-09-29) Lightning indexer + fine-grained token selection. The first frontier model where sparse attention is the production path, not an ablation. MMLU-Pro 85.0 (par with V3.1-Terminus dense). AIME 2025: 89.3 vs 88.4. API price cut >50%.

SSA — Subquadratic Selective Attention (Subquadratic, launched 2026-05-05) Content-dependent selection. 1M tokens production, 12M tokens research. Claims 52× speedup at 1M tokens vs FlashAttention-2 on B200s. Independent benchmarks pending — discount accordingly.

What it means for your stack today:

  • SGLang v0.5.9 ships TRT-LLM DSA kernels. Flag: --nsa-prefill-backend trtllm. 3–5× speedup on Blackwell.
  • A 1M-token system prompt is now a budget question, not a research project.
  • Long-context evals get harder, not easier. Sparse models pass needle-in-haystack and still miss multi-hop reasoning at depth — your eval harness needs a long-context reasoning section, not just retrieval.

The trap: subquadratic is a complexity class, not a quality guarantee. Mamba and RWKV were both subquadratic. Both ended up hybrid. Bet on architectures that ship par-quality benchmarks, not ones that ship throughput plots.

Sources
  1. NSA paper (DeepSeek, ACL 2025)
  2. DeepSeek-V3.2-Exp release
  3. DeepSeek-V3.2 paper
  4. SGLang DSA support
  5. Subquadratic launch coverage (independent)
  6. Subquadratic skepticism coverage