[Model] Use explicit types in get_generation_prompt (#33551)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/models/gemma3n_mm.py

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from collections.abc import Iterable, Mapping, Sequence
-from typing import Annotated, Any, Literal, cast
+from typing import Annotated, Any, Literal
 
 import numpy as np
 import torch
@@ -19,7 +19,7 @@ from transformers.models.siglip import SiglipImageProcessorFast
 
 from vllm.config import ModelConfig, SpeechToTextConfig, VllmConfig
 from vllm.config.multimodal import BaseDummyOptions
-from vllm.inputs.data import PromptType
+from vllm.inputs.data import PromptType, TextPrompt
 from vllm.logger import init_logger
 from vllm.model_executor.layers.layernorm import RMSNorm
 from vllm.model_executor.layers.linear import RowParallelLinear
@@ -807,9 +807,10 @@ class Gemma3nForConditionalGeneration(
 
         prompt += ": <audio_soft_token><end_of_turn>\n<start_of_turn>model\n"
 
-        audio = (audio, stt_config.sample_rate)
-        prompts_dict = {"multi_modal_data": {"audio": audio}, "prompt": prompt}
-        return cast(PromptType, prompts_dict)
+        return TextPrompt(
+            prompt=prompt,
+            multi_modal_data={"audio": (audio, stt_config.sample_rate)},
+        )
 
     @classmethod
     def get_speech_to_text_config(