Decoding

Walk through how top_p (nucleus) sampling truncates the distribution

Compare top_k and top_p as truncation strategies for sampling

How does the temperature parameter reshape the sampling distribution?

Define a stop sequence in an LLM API call

Server-Sent Events streaming: define it and explain why chat APIs default to it

max_tokens vs stop: pair each parameter with the cap it enforces on the completion.

Pair each decoding strategy with its determinism and diversity profile.

Describe what 'autoregressive' means for LLM generation.

Attention temperature divides QK^T; sampling temperature divides output logits, distinguishwhere each lives.

Flashcard: what does the temperature parameter do during LLM generation and how should you set it?

Why do production chat APIs almost never offer beam search as a decoding option?