Story

arxiv_cs_lg ยท Nov 19, 2026 ยท paper

Source brief

DTS: Delta-Based Tile Scoring for Efficient Long-Context Sparse Attention

arxiv.orgNov 19, 2026
original source linked

In brief

Large language models (LLMs) increasingly need to process long documents and codebases, making long-context attention a major prefill bottleneck. Block sparse attention reduces computation by skipping unimportant bloc...

Feed lens
eval

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items