[diffusion][feature] Add offline SVDQuant W4A4 support (#6162)

Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/model_executor/models/test_encoder_quant_config.py

@@ -1,12 +1,12 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 """Regression test for #2686: pre-quantized methods must not apply
 quant config to vision / audio encoders.
 
-For modelopt FP8/FP4/MXFP8 checkpoints the Thinker LM is the only
-quantized component.  Vision and audio encoder weights are BF16 with no
-FP8 scale tensors — passing quant_config to them causes FP8 kernels to
-run on BF16 weights, producing garbage embeddings.
+For serialized ModelOpt and SVDQuant checkpoints the target model component is
+the only quantized component. Vision and audio encoder weights are BF16 with no
+serialized scale or correction tensors, so the same config must not be applied
+to them.
 
 **Import note (pytest + ``tests/model_executor`` only):** :mod:`vllm_omni.quantization`
 :file:`__init__` pulls ``factory``/``inc`` and reproduces vLLM CustomOp double
@@ -58,8 +58,7 @@ pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 @pytest.mark.parametrize("method", sorted(PRE_QUANTIZED_METHODS))
 def test_pre_quantized_returns_none(method: str) -> None:
     """visual_quant_config and audio_quant_config must be None for
-    pre-quantized methods (modelopt, modelopt_fp4, modelopt_mxfp8,
-    modelopt_mixed)."""
+    pre-quantized methods (ModelOpt variants and SVDQuant)."""
     mock_config = MagicMock()
     mock_config.get_name.return_value = method
 
@@ -101,5 +100,5 @@ def test_component_config_passed_through() -> None:
 
 def test_pre_quantized_methods_contains_expected() -> None:
     """Guard against accidental removal of a known pre-quantized method."""
-    expected = {"modelopt", "modelopt_fp4", "modelopt_mxfp8", "modelopt_mixed"}
+    expected = {"modelopt", "modelopt_fp4", "modelopt_mxfp8", "modelopt_mixed", "svdquant"}
     assert PRE_QUANTIZED_METHODS == expected