[VLM] Merged multi-modal processor for InternVL-based models (#12553)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>

tests/models/multimodal/processing/test_common.py

@@ -141,13 +141,14 @@ def _test_processing_correctness(
 
 
 # yapf: disable
-# True if the model supports multiple data items of the modality per request
 @pytest.mark.parametrize("model_id", [
     "rhymes-ai/Aria",
     "Salesforce/blip2-opt-2.7b",
     "facebook/chameleon-7b",
     "deepseek-ai/deepseek-vl2-tiny",
     "adept/fuyu-8b",
+    "h2oai/h2ovl-mississippi-800m",
+    "OpenGVLab/InternVL2-1B",
     "llava-hf/llava-1.5-7b-hf",
     "llava-hf/llava-v1.6-mistral-7b-hf",
     "llava-hf/LLaVA-NeXT-Video-7B-hf",
@@ -156,6 +157,7 @@ def _test_processing_correctness(
     "mistral-community/pixtral-12b",
     "openbmb/MiniCPM-o-2_6",
     "openbmb/MiniCPM-V-2_6",
+    "nvidia/NVLM-D-72B",
     "Qwen/Qwen-VL-Chat",
     "Qwen/Qwen2-VL-2B-Instruct",
     "Qwen/Qwen2-Audio-7B-Instruct",