DeepSeek

Which sublayer of a dense transformer block carries more parameters, attention or FFN?

Why has GRPO eaten PPO's lunch in 2025-2026 reasoning post-training?

What does the dot product q . k actually measure inside an attention layer?

Decoder-only LLMs ship without a cross-attention sub-layer, so where does the context go?

Decode-phase attention is memory bandwidth bound. Explain what flips the regime.

Walk through a T5 decoder block in order, list the attention sub-layers and what each one's Q, K, V read from.

Bi-encoders vs cross-encoders, where does attention cross the query and document?

Describe how continuous batching interacts with the KV cache

Identify the context vector inside scaled dot-product attention and what produces it.

BERT prepends a [CLS] token to every input, what is its actual job in the model?