Skip to content
conftrace_

long-sequence inference

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sparse attention (2) multi-context inference (1) prefilling phase (1) computational budget (1) key-value cache (1) retrieval-augmented generation (1) throughput optimization (1)

Papers

Sparse Attention Across Multiple-Context KV Cache AAAI 2026 FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference ICLR 2025