[Model] Add T5Gemma2 model plugin integration

Author: akh64bit

vllm_bart_plugin/__init__.py

@@ -33,6 +33,10 @@ def register_bart_model() -> None:
             "Florence2ForConditionalGeneration",
             "vllm_bart_plugin.florence2:Florence2ForConditionalGeneration",
         )
+        ModelRegistry.register_model(
+            "T5Gemma2ForConditionalGeneration",
+            "vllm_bart_plugin.t5gemma2:T5Gemma2ForConditionalGeneration",
+        )
 
         logger.info("Successfully registered BART model with vLLM")
 

vllm_bart_plugin/bart.py

@@ -29,7 +29,8 @@
 from torch import nn
 from transformers import BartConfig
 from transformers.utils import logging
-from vllm.attention.layer import Attention, AttentionType
+from vllm.model_executor.layers.attention import Attention
+from vllm.v1.attention.backend import AttentionType
 from vllm.config import CacheConfig, VllmConfig
 from vllm.config.lora import LoRAConfig
 from vllm.config.multimodal import BaseDummyOptions
@@ -78,7 +79,7 @@
     EncDecMultiModalProcessor,
     PromptUpdate,
 )
-from vllm.multimodal.profiling import BaseDummyInputsBuilder
+from vllm.multimodal.processing import BaseDummyInputsBuilder
 from vllm.sequence import IntermediateTensors
 from vllm.utils.collection_utils import is_list_of
 

vllm_bart_plugin/florence2.py

@@ -13,7 +13,8 @@
 from transformers import BartConfig, BatchFeature, BartTokenizer, PretrainedConfig
 from transformers.utils import logging
 
-from vllm.attention.layer import Attention, AttentionType
+from vllm.model_executor.layers.attention import Attention
+from vllm.v1.attention.backend import AttentionType
 from vllm.model_executor.layers.attention.cross_attention import CrossAttention
 from vllm.model_executor.layers.attention.mm_encoder_attention import MMEncoderAttention
 from vllm.config import CacheConfig, VllmConfig
@@ -53,7 +54,7 @@
     PromptInsertion,
     PromptIndexTargets,
 )
-from vllm.multimodal.profiling import BaseDummyInputsBuilder
+from vllm.multimodal.processing import BaseDummyInputsBuilder
 from vllm.sequence import IntermediateTensors
 from vllm.utils.collection_utils import is_list_of