[Core][Frontend] Support Passing Multimodal Processor Kwargs (#8657)

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

tests/models/utils.py

@@ -1,6 +1,8 @@
 import warnings
 from typing import Dict, List, Optional, Sequence, Tuple, Union
 
+from vllm.config import ModelConfig
+from vllm.inputs import InputContext
 from vllm.sequence import Logprob, PromptLogprobs, SampleLogprobs
 
 TokensText = Tuple[List[int], str]
@@ -240,3 +242,36 @@ def check_logprobs_close(
                     warnings.simplefilter("always")
 
                     warnings.warn(fail_msg, stacklevel=2)
+
+
+def build_model_context(model_name: str,
+                        tokenizer_name: Optional[str] = None,
+                        trust_remote_code: bool = False,
+                        mm_processor_kwargs: Optional[Dict] = None,
+                        limit_mm_per_prompt: Optional[Dict] = None):
+    """Creates an InputContext for a given model.
+    
+    Args:
+        model_name: Name of the model being considered.
+        tokenizer_name: Name of the tokenizer being considered.
+        trust_remote_code: Whether or not to allow loading remote code.
+        mm_processor_kwargs: optional processor kwargs for to be leveraged
+            in the input processor, mapper, dummy data creation, etc.
+        limit_mm_per_prompt: Multimodal limits.
+
+    Returns:
+        InputContext for the model being considered.
+    """
+    if tokenizer_name is None:
+        tokenizer_name = model_name
+    model_config = ModelConfig(
+        model_name,
+        tokenizer_name,
+        tokenizer_mode="auto",
+        trust_remote_code=trust_remote_code,
+        dtype="float32",
+        seed=0,
+        mm_processor_kwargs=mm_processor_kwargs,
+        limit_mm_per_prompt=limit_mm_per_prompt,
+    )
+    return InputContext(model_config)