[VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126)

docs/source/dev/input_processing/input_processing_pipeline.rst

@@ -17,4 +17,4 @@ Input Processing Pipeline
 
 6. If the data contains multi-modal data, convert it into keyword arguments using :meth:`MULTIMODAL_REGISTRY.map_input <vllm.multimodal.MultiModalRegistry.map_input>`.
 
-   - For example, convert a :class:`PIL.Image.Image` input to its pixel values for a vision language model.
+   - For example, convert a :class:`PIL.Image.Image` input to its pixel values for a vision model.

docs/source/dev/multimodal/multimodal_index.rst

@@ -15,6 +15,9 @@ by following :ref:`this guide <adding_multimodal_plugin>`.
 
 Looking to add your own multi-modal model? Please follow the instructions listed :ref:`here <enabling_multimodal_inputs>`.
 
+..
+  TODO: Add usage of --limit-mm-per-prompt when multi-image input is officially supported
+
 Guides
 ++++++
 

docs/source/models/enabling_multimodal_inputs.rst

@@ -66,7 +66,7 @@ A default mapper is available for each modality in the core vLLM library. This i
 3. Register maximum number of multi-modal tokens
 ------------------------------------------------
 
-For each modality type that the model accepts as input, calculate the maximum possible number of tokens
+For each modality type that the model accepts as input, calculate the maximum possible number of tokens per data instance
 and register it via :meth:`INPUT_REGISTRY.register_dummy_data <vllm.inputs.registry.InputRegistry.register_max_multimodal_tokens>`.
 
 .. code-block:: diff