IndexCache, a new sparse attention optimizer, delivers 1.82x faster inference on long-context AI models

Researchers at Tsinghua University and Z.ai built IndexCache to eliminate redundant computation in sparse attention models ...
The New York Times

Hard Fork

Companies are using A.I. as a reason for layoffs, but the truth may be more complex. By Kevin RooseCasey NewtonRachel CohnWhitney JonesVjeran PavicKatie McMurranDan PowellRowan Niemisto and Diane Wong ...