From a91e072f333d0e83e5a7256d706d04265c8bc678 Mon Sep 17 00:00:00 2001 From: Kangyan-Zhou Date: Thu, 25 Dec 2025 18:45:57 -0800 Subject: [PATCH] Use allow auto truncate in the OpenAI API endpoint (#15369) --- python/sglang/srt/entrypoints/openai/serving_chat.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sglang/srt/entrypoints/openai/serving_chat.py b/python/sglang/srt/entrypoints/openai/serving_chat.py index 354aa6c1d..cb0c084a3 100644 --- a/python/sglang/srt/entrypoints/openai/serving_chat.py +++ b/python/sglang/srt/entrypoints/openai/serving_chat.py @@ -133,7 +133,7 @@ class OpenAIServingChat(OpenAIServingBase): max_output_tokens and server_context_length and max_output_tokens > server_context_length - ): + ) and not self.tokenizer_manager.server_args.allow_auto_truncate: return ( f"max_completion_tokens is too large: {max_output_tokens}." f"This model supports at most {server_context_length} completion tokens."