diff --git a/examples/offline_inference/qwen_2_5_omni/run.sh b/examples/offline_inference/qwen_2_5_omni/run.sh
index bee28e2c4..7f02a672c 100644
--- a/examples/offline_inference/qwen_2_5_omni/run.sh
+++ b/examples/offline_inference/qwen_2_5_omni/run.sh
@@ -1,9 +1,8 @@
 export PYTHONPATH=/path/to/vllm-omni:$PYTHONPATH
 python end2end.py --model Qwen/Qwen2.5-Omni-7B \
+                                 --prompts "Explain the system architecture for a scalable audio generation pipeline. Answer in 15 words." \
                                  --voice-type "m02" \
                                  --dit-ckpt none \
                                  --bigvgan-ckpt none \
                                  --output-wav output_audio \
-                                 --prompt_type text \
-                                 --init-sleep-seconds 0 \
-                                 --pt-prompts top100.pt
+                                 --prompt_type text
diff --git a/examples/offline_inference/qwen_2_5_omni/utils.py b/examples/offline_inference/qwen_2_5_omni/utils.py
index 42894c4a7..730d2a077 100644
--- a/examples/offline_inference/qwen_2_5_omni/utils.py
+++ b/examples/offline_inference/qwen_2_5_omni/utils.py
@@ -13,10 +13,6 @@ from processing_omni import fetch_image, fetch_video
 from vllm.inputs import TextPrompt
 from vllm_omni.inputs.data import OmniTokensPrompt
 
-# Simple caches to avoid repeated heavy HF loads per prompt
-_PROCESSOR_CACHE: Dict[str, "AutoProcessor"] = {}
-_CONFIG_CACHE: Dict[str, "AutoConfig"] = {}
-
 
 def get_system_prompt():
 
@@ -117,25 +113,16 @@ def make_inputs_qwen2_omni(
 
     from transformers import AutoConfig, AutoProcessor
 
-    # Cached processor/config to prevent per-prompt reloading and repeated warnings
-    if args.model not in _PROCESSOR_CACHE:
-        _PROCESSOR_CACHE[args.model] = AutoProcessor.from_pretrained(args.model)
-    processor = _PROCESSOR_CACHE[args.model]
+    processor = AutoProcessor.from_pretrained(args.model)
 
-    config = _CONFIG_CACHE.get(args.model)
-    if config is None:
-        try:
-            config = AutoConfig.from_pretrained(args.model)
-        except Exception:
-            config = None
-        _CONFIG_CACHE[args.model] = config  # cache even if None to avoid retry storms
-
-    # Decide legacy flag only once based on config (default True if unknown)
-    if getattr(args, "legacy_omni_video", None) is None:
-        if config is not None and hasattr(config, "architectures"):
-            args.legacy_omni_video = not ("Qwen2_5OmniModel" in config.architectures)
+    try:
+        config = AutoConfig.from_pretrained(args.model)
+        if "Qwen2_5OmniModel" in config.architectures:
+            args.legacy_omni_video = False
         else:
             args.legacy_omni_video = True
+    except Exception:
+        args.legacy_omni_video = True
 
     audios, images, videos = [], [], []
     for message in messages: