Understanding EOS, stop_token_ids, and stop_sequences in vLLM
This article dissects how vLLM handles generation termination by comparing token‑level EOS, token‑level stop_token_ids, and string‑level stop/stop_sequences, detailing where each check occurs, how they affect the Scheduler and Detokenizer, and how finish_reason and stop_reason are derived for the API response.
