Architecture
aka Rotary Position Embedding

RoPE

Position-encoding scheme that rotates query/key vectors in 2D subspaces by their position.

Definition

Rotary position embedding (Su et al. 2021) encodes positions as rotation matrices applied to query/key pairs, naturally generalising to longer contexts than seen at training. RoPE is used in Llama, Qwen, Mistral and most modern decoder-only LLMs.

Common use cases

  • Long-context extension
  • Modern LLMs
  • Position embeddings

Related terms

    RoPE — AI Glossary | Railwail