[AutoRound] Add offline quantized W4A16 model support (#1777)

Signed-off-by: yiliu30 <yi4.liu@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/diffusion/data.py

@@ -193,12 +193,24 @@ class TransformerConfig:
     """Container for raw transformer configuration dictionaries."""
 
     params: dict[str, Any] = field(default_factory=dict)
+    quant_method: str | None = None
+    quant_config: "QuantizationConfig | None" = None
 
     @classmethod
     def from_dict(cls, data: dict[str, Any]) -> "TransformerConfig":
         if not isinstance(data, dict):
             raise TypeError(f"Expected transformer config dict, got {type(data)!r}")
-        return cls(params=dict(data))
+        params = dict(data)  # copy to avoid mutating caller's dict
+
+        quant_method: str | None = None
+        quant_config: QuantizationConfig | None = None
+        disk_qc = params.get("quantization_config")
+        if isinstance(disk_qc, dict) and "quant_method" in disk_qc:
+            quant_method = disk_qc["quant_method"]
+            kwargs = {k: v for k, v in disk_qc.items() if k != "quant_method"}
+            quant_config = build_quant_config(quant_method, **kwargs)
+
+        return cls(params=params, quant_method=quant_method, quant_config=quant_config)
 
     def to_dict(self) -> dict[str, Any]:
         return dict(self.params)
@@ -598,6 +610,17 @@ class OmniDiffusionConfig:
             # If it's neither dict nor DiffusionCacheConfig, convert to empty config
             self.cache_config = DiffusionCacheConfig()
 
+        # Auto-detect quantization from TransformerConfig if not explicitly set.
+        # This covers the case where tf_model_config is passed at construction
+        # time.  For late (post-construction) assignment, callers should use
+        # set_tf_model_config() which propagates quant_config automatically.
+        if self.quantization_config is None and self.tf_model_config.quant_config is not None:
+            self.quantization_config = self.tf_model_config.quant_config
+            logger.info(
+                "Auto-detected quantization '%s' from model config",
+                self.tf_model_config.quant_method,
+            )
+
         # Resolve quantization_config: str/dict -> QuantizationConfig via build_quant_config.
         if self.quantization_config is not None:
             if isinstance(self.quantization_config, QuantizationConfig):
@@ -617,6 +640,28 @@ class OmniDiffusionConfig:
         elif self.max_cpu_loras < 1:
             raise ValueError("max_cpu_loras must be >= 1 for diffusion LoRA")
 
+    def set_tf_model_config(self, tf_config: "TransformerConfig") -> None:
+        """Assign `tf_model_config` and propagate quantization if detected.
+
+        In the normal startup flow `OmniDiffusionConfig` is created
+        *before* the transformer `config.json` is loaded from disk, so
+        `__post_init__` sees an empty `TransformerConfig`.  Callers
+        that load the config later should use this method instead of bare
+        assignment so that an embedded `quant_config` is propagated to
+        `self.quantization_config` automatically.
+
+        Args:
+            tf_config: Transformer configuration, typically built via
+                `TransformerConfig.from_dict`.
+        """
+        self.tf_model_config = tf_config
+        if self.quantization_config is None and tf_config.quant_config is not None:
+            self.quantization_config = tf_config.quant_config
+            logger.info(
+                "Auto-detected quantization '%s' from model config",
+                tf_config.quant_method,
+            )
+
     def update_multimodal_support(self) -> None:
         self.supports_multimodal_inputs = self.model_class_name in {"QwenImageEditPlusPipeline"}