VINDEX3

A CONCEPT · PROJECTED FROM THE VINDEX KNOWLEDGE GRAPH

MLA — MULTI-HEAD LATENT ATTENTION

the cache compressed through latents

An attention family that stores its key/value past through a low-rank latent bottleneck — full-attention memory at a fraction of the cache bytes.

Its surface declares num_heads · kv_lora_rank · qk_nope_head_dim · qk_rope_head_dim · v_head_dim: the rope and no-rope halves of the key are separate declared facts, and the latent A/B projections with their norm are operands like any others. It keeps true KV state — compressed, not replaced.

IN THE GRAPH

mla — multi-head latent attentionsibling ofattention

mla — multi-head latent attentionsibling ofkda — kimi delta attention

mla — multi-head latent attentiondistinguished bykv state vs recurrent state