From edac7e2e24f1eb342585fe5beda81fc91c676f6a Mon Sep 17 00:00:00 2001 From: Seth Kimmel Date: Tue, 5 Aug 2025 11:59:07 -0700 Subject: [PATCH] Update run-vllm.md --- articles/gpt-oss/run-vllm.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/articles/gpt-oss/run-vllm.md b/articles/gpt-oss/run-vllm.md index fc70d119f0..ee9619a1bf 100644 --- a/articles/gpt-oss/run-vllm.md +++ b/articles/gpt-oss/run-vllm.md @@ -197,7 +197,7 @@ convo = Conversation.from_messages( prefill_ids = encoding.render_conversation_for_completion(convo, Role.ASSISTANT) # Harmony stop tokens (pass to sampler so they won't be included in output) -stop_token_ids = encoding.stop_tokens_for_assistant_action() +stop_token_ids = encoding.stop_tokens_for_assistant_actions() # --- 2) Run vLLM with prefill --- llm = LLM(