From e729cc823d313aa7623ecadefe4305ea241c3dce Mon Sep 17 00:00:00 2001 From: San-Nguyen Date: Mon, 20 Apr 2026 02:25:06 -0500 Subject: [PATCH] [Fix] Add Spacing when Requesting Output Token > max_model_len (#40324) Signed-off-by: San-Nguyen --- vllm/renderers/params.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/renderers/params.py b/vllm/renderers/params.py index a2c95690c79..10bc01043f7 100644 --- a/vllm/renderers/params.py +++ b/vllm/renderers/params.py @@ -204,7 +204,7 @@ class TokenizeParams: and max_output_tokens > max_total_tokens ): raise VLLMValidationError( - f"{self.max_output_tokens_param}={max_output_tokens}" + f"{self.max_output_tokens_param}={max_output_tokens} " f"cannot be greater than " f"{self.max_total_tokens_param}={max_total_tokens=}. " f"Please request fewer output tokens.",