[AutoRound] Support Qwen Omni W4A16 quantization model

docs/user_guide/diffusion/quantization/autoround.md

@@ -72,6 +72,8 @@ At load time:
 | Model | HF Checkpoint | Scheme | Group Size | Backend |
 |-------|--------------|--------|------------|---------|
 | FLUX.1-dev | `vllm-project-org/FLUX.1-dev-AutoRound-w4a16` | W4A16 | 128 | GPTQ-Marlin |
+| Qwen2.5-Omni-7B | `Intel/Qwen2.5-Omni-7B-int4-AutoRound` | W4A16 | 128 | GPTQ-Marlin |
+| Qwen3-Omni-30B-A3B-Instruct | `Intel/Qwen3-Omni-30B-A3B-Instruct-int4-AutoRound` | W4A16 | 128 | GPTQ-Marlin |
 
 ## Creating a Quantized Checkpoint
 

examples/offline_inference/qwen2_5_omni/end2end.py

@@ -5,6 +5,7 @@
 with the correct prompt format on Qwen2.5-Omni
 """
 
+import json
 import os
 import time
 from typing import NamedTuple
@@ -289,7 +290,10 @@ def get_audio_query(question: str = None, audio_path: str | None = None, samplin
 
 
 def main(args):
-    model_name = "Qwen/Qwen2.5-Omni-7B"
+    model_name = args.model
+    quantization_config = None
+    if args.quantization_config is not None:
+        quantization_config = json.loads(args.quantization_config)
 
     # Get paths from args
     video_path = getattr(args, "video_path", None)
@@ -320,6 +324,7 @@ def main(args):
         query_result = query_func(audio_path=audio_path, sampling_rate=sampling_rate)
     else:
         query_result = query_func()
+    args.quantization_config = quantization_config
     omni = Omni.from_cli_args(args, model=model_name)
     thinker_sampling_params = SamplingParams(
         temperature=0.0,  # Deterministic - no randomness
@@ -424,6 +429,18 @@ def main(args):
 
 def parse_args():
     parser = FlexibleArgumentParser(description="Demo on using vLLM for offline inference with audio language models")
+    parser.add_argument(
+        "--model",
+        type=str,
+        default="Qwen/Qwen2.5-Omni-7B",
+        help="Model name or local path.",
+    )
+    parser.add_argument(
+        "--quantization-config",
+        type=str,
+        default=None,
+        help="Optional JSON string forwarded to Omni(quantization_config=...).",
+    )
     parser.add_argument(
         "--query-type",
         "-q",