[Model] Fix Gemma 4 token repetition by dynamic BOS injection for PT models (#39842)

Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
(cherry picked from commit 6dc94914)

vllm/model_executor/models/gemma4_mm.py

@@ -168,9 +168,14 @@ class Gemma4ProcessingInfo(BaseProcessingInfo):
 
         Setting ``add_special_tokens=False`` here prevents the duplicate and
         ensures both ``llm.generate()`` and the chat/completions API behave
-        correctly.
+        correctly for IT models. For PT models (without chat template), we
+        keep the default (True) to ensure BOS is added for raw prompts.
         """
+        tokenizer = self.ctx.get_tokenizer()
+        has_chat_template = getattr(tokenizer, "chat_template", None) is not None
+
         params = super().get_default_tok_params()
+        if has_chat_template:
             params = params.with_kwargs(add_special_tokens=False)
         return params