
Zyphra introduces Hierarchical Attention for subquadratic attention
The available text names ZHA but gives no architecture, benchmarks, or release details.
2 stories, newest first · one card per story

The available text names ZHA but gives no architecture, benchmarks, or release details.
SQD disaggregates LLM inference by quadratic versus subquadratic attention layers, improving energy efficiency up to 56% on heterogeneous systems versus GPU-only baselines.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views