[Model] rename NemotronH_Nano_VL -> NemotronH_Nano_VL_V2 (#25708)

Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>

tests/models/registry.py

@@ -531,7 +531,7 @@ _MULTIMODAL_EXAMPLE_MODELS = {
                               trust_remote_code=True),
     "Llama_Nemotron_Nano_VL" : _HfExamplesInfo("nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1", # noqa: E501
                                                      trust_remote_code=True),
-    "NemotronH_Nano_VL": _HfExamplesInfo("nano_vl_dummy",
+    "NemotronH_Nano_VL_V2": _HfExamplesInfo("nano_vl_dummy",
                                           is_available_online=False,
                                           trust_remote_code=True),
     "Ovis": _HfExamplesInfo("AIDC-AI/Ovis2-1B", trust_remote_code=True,

vllm/model_executor/models/nano_nemotron_vl.py

@@ -869,7 +869,7 @@ class NanoNemotronVLDummyInputsBuilder(
     info=NanoNemotronVLProcessingInfo,
     dummy_inputs=NanoNemotronVLDummyInputsBuilder,
 )
-class NemotronH_Nano_VL(nn.Module, HasInnerState, IsHybrid,
+class NemotronH_Nano_VL_V2(nn.Module, HasInnerState, IsHybrid,
                            SupportsMultiModal):
 
     @classmethod
@@ -1249,7 +1249,7 @@ class NemotronH_Nano_VL(nn.Module, HasInnerState, IsHybrid,
 
         try:
             print("=" * 100)
-            print("NemotronH_Nano_VL Model Architecture")
+            print("NemotronH_Nano_VL_V2 Model Architecture")
             print("=" * 100)
 
             total_params = 0
@@ -1333,7 +1333,7 @@ class NemotronH_Nano_VL(nn.Module, HasInnerState, IsHybrid,
             component_info[component]["size"] += param.numel()
 
         return {
-            "model_name": "NemotronH_Nano_VL",
+            "model_name": "NemotronH_Nano_VL_V2",
             "total_parameters": total_params,
             "memory_estimate_mb": total_params * 2 / (1024**2),  # bfloat16
             "components": component_info,

vllm/model_executor/models/registry.py

@@ -231,7 +231,7 @@ _MULTIMODAL_MODELS = {
     "GraniteSpeechForConditionalGeneration": ("granite_speech", "GraniteSpeechForConditionalGeneration"),  # noqa: E501
     "H2OVLChatModel": ("h2ovl", "H2OVLChatModel"),
     "InternVLChatModel": ("internvl", "InternVLChatModel"),
-    "NemotronH_Nano_VL": ("nano_nemotron_vl", "NemotronH_Nano_VL"),
+    "NemotronH_Nano_VL_V2": ("nano_nemotron_vl", "NemotronH_Nano_VL_V2"),
     "InternS1ForConditionalGeneration": ("interns1", "InternS1ForConditionalGeneration"),  # noqa: E501
     "InternVLForConditionalGeneration": ("interns1", "InternS1ForConditionalGeneration"),  # noqa: E501
     "Idefics3ForConditionalGeneration":("idefics3","Idefics3ForConditionalGeneration"),