Joint Subspace Sparse Attention for Efficient Long-Context Decoding
arXiv:2610.19026v1 Announce Type: new Abstract: Sparse attention reduces the KV-cache traffic that dominates long-context LLM decoding, but practical methods largely operate at coarse granularity. Token-level selection offers finer control, yet presents two challenges: low-dimensional scoring may l…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-15 04:00 · arXiv cs.CL
Joint Subspace Sparse Attention for Efficient Long-Context Decoding