feat(model): Add BitsAndBytes quantization support for Qwen3-Omni-MoE (#29896)

Signed-off-by: navanit-git <navanitdubey@gmail.com>

vllm/model_executor/models/qwen3_omni_moe_thinker.py

@@ -62,6 +62,7 @@ from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
+from vllm.model_executor.models.module_mapping import MultiModelKeys
 from vllm.model_executor.models.qwen2_audio import Qwen2AudioProcessingInfo
 from vllm.multimodal import MULTIMODAL_REGISTRY
 from vllm.multimodal.inputs import MultiModalFeatureSpec, MultiModalKwargsItems
@@ -1137,6 +1138,18 @@ class Qwen3OmniMoeThinkerForConditionalGeneration(
         }
     )
 
+    packed_modules_mapping = {
+        "qkv_proj": [
+            "q_proj",
+            "k_proj",
+            "v_proj",
+        ],
+        "gate_up_proj": [
+            "gate_proj",
+            "up_proj",
+        ],
+    }
+
     @classmethod
     def get_placeholder_str(cls, modality: str, i: int) -> str | None:
         if modality.startswith("image"):
@@ -1763,3 +1776,13 @@ class Qwen3OmniMoeThinkerForConditionalGeneration(
 
         mrope_position_delta = llm_positions.max() + 1 - seq_len
         return llm_positions, mrope_position_delta
+
+    def get_mm_mapping(self) -> MultiModelKeys:
+        """
+        Get the module prefix in multimodal models
+        """
+        return MultiModelKeys.from_string_field(
+            language_model="language_model",
+            connector="visual.merger",
+            tower_model=["visual.", "audio_tower."],
+        )