Encoder Decoder

Where does cross-attention live in OpenAI Whisper?

Inside a T5 style encoder-decoder, which sub-layer reads the encoder outputs, and through which projection?

Identify the attention side optimization when translating one source sentence into many target languages

Explain how decoder-only LLMs condition on context without a cross-attention sub-layer

Order the attention sub-layers in a T5 decoder block and what each one's Q, K, and V read from in self-attention versus in cross-attention.

Explain the difference between self-attention and cross-attention. When does each appear in a real architecture?

PremiumWhich modern LLM architecture…