Skip to content

Published collection

SparDA uses Forecast projections to select next-layer KV blocks

This method targets the cost of KV cache selection in long-context reasoning and may improve sparse attention efficiency.

Updated
Editorial
Frontline Lab
Published entries
1
Sources
1
Date range
2026-08-12
Primary labels
Research · 论文 · Training Methods · SparDA · NVIDIA · DeepSeek

Published evidence

Every entry keeps its summary and a path back to the source context.