ConceptAI & ML
Caching vector comparisons
Precomputing and pulling vector comparisons from memory to reduce the self-attention layer's computational cost from quadratic to linear.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.