Multi-Latent Attention

Concept

A DeepSeek innovation that compresses key and value projections to reduce KV cache size, improving efficiency.

Mentioned in 1 video

Videos Mentioning Multi-Latent Attention

Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 10: Inference

Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 10: Inference

Stanford Online

A DeepSeek innovation that compresses key and value projections to reduce KV cache size, improving efficiency.