Tweet by fergal_reid

April 9, 2026

We’re excited to share our new form of attention, Low Rank Key Value attention. This is a drop-in replacement to standard MHA that in our tests, reduces KV-cache by ~50%, with even lower test loss, across many scales of experiment. https://t.co/JdQddhehuj

Author
fergal_reid
Date
April 9, 2026