AI inference glossary
Model architectureMLA

Multi-head latent attention

In plain English

MLA compresses the model’s notes about earlier tokens so long conversations use less memory and are cheaper to continue.

Technical definition

Multi-head latent attention compresses attention key and value state into a lower-dimensional latent representation to reduce KV-cache size and memory traffic.

Engineering details

Instead of storing full per-head keys and values for every prior token, MLA stores compressed state and reconstructs or consumes the needed representations through model-specific projections. Implementations require specialized attention kernels.

Why it matters

Reducing KV-cache bytes increases feasible context length and concurrency and can lower decode bandwidth pressure. Kernel shape support and tensor-parallel layout can still create large performance differences.

How to read it in InferenceX

Several DeepSeek-derived models in InferenceX use MLA. Articles track fixes where an attention backend handled one heads-per-rank shape efficiently but failed or fell back on another.