[Core] Initialize LoRA support for tower and connector in multi-modal models (#26674)

Signed-off-by: bk-201 <joy25810@foxmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: prashanth058 <prashanth.dannamaneni@uipath.com>
Co-authored-by: bk-201 <joy25810@foxmail.com>
Co-authored-by: prashanth058 <prashanth.dannamaneni@uipath.com>
Co-authored-by: Anexdeus <5142168@mail.ru>

vllm/model_executor/models/qwen2_vl.py

@@ -1491,6 +1491,25 @@ class Qwen2VLForConditionalGeneration(
             tower_model="visual.",
         )
 
+    def get_num_mm_encoder_tokens(
+        self,
+        num_image_tokens: int,
+    ) -> int:
+        hf_config = self.config
+        vision_config = hf_config.vision_config
+        merge_size = vision_config.spatial_merge_size
+
+        return num_image_tokens * merge_size**2
+
+    def get_num_mm_connector_tokens(
+        self,
+        num_vision_tokens: int,
+    ) -> int:
+        hf_config = self.config
+        vision_config = hf_config.vision_config
+        merge_size = vision_config.spatial_merge_size
+        return num_vision_tokens // merge_size**2
+
 
 class Tarsier2MultiModalProcessor(Qwen2VLMultiModalProcessor):
     pass