← Wednesday, October 14, 2026InferencePaper

DoSA skips unnecessary sparse-attention scores with exact selection guarantees

huggingface.co by Fanxu Meng, Taosong Fang Editor score 9/10

DoSA uses score bounds to avoid fully scoring candidates that cannot enter Top-K, reporting up to 2.74× Indexer speedup and up to 1.94× time-to-first-token speedup. Its exact-selection approach offers a concrete path to faster sparse-attention serving.

What: - DoSA is a lossless method that makes sparse-attention scoring conditional while preserving exact token selection.
Method: - A seed-set threshold and bounds certify which candidates can be rejected; only still-eligible candidates receive full scoring, followed by exact-score filtering.
Why it matters: - The GPU implementation accelerates the complete Indexer by up to 2.74× over SGLang, reducing attention-indexing work without approximate selection.

Bounds and a seed-set threshold guide candidates through exact scoring and filtering. Sketched from the article's own text.

Read on huggingface.co → Code · 5 stars

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.