Update docs

vllm-project · Oct 22, 2024 · e4c8cc4 · e4c8cc4
1 parent c8b41c3
commit e4c8cc4
Showing 1 changed file with 8 additions and 3 deletions.
diff --git a/docs/source/models/supported_models.rst b/docs/source/models/supported_models.rst
@@ -345,7 +345,7 @@ Text Generation
 
   * - Architecture
     - Models
-    - Inputs
+    - Inputs\*
     - Example HF Models
     - :ref:`LoRA <lora>`
     - :ref:`PP <distributed_serving>`
@@ -464,6 +464,8 @@ Text Generation
     -
     - ✅︎
 
+| \*Any combination of modalities joined by :code:`+` are supported. For example, :code:`T + I` means that the model supports text-only, image-only, and text-with-image inputs.
+  On the other hand, modalities separated by :code:`/` are mutually exclusive. For example :code:`T / I` means that the model supports text-only and image-only inputs, but not text-with-image inputs.
 | :sup:`E` Pre-computed embeddings can be inputted for this modality.
 | :sup:`+` Multiple items can be inputted per text prompt for this modality.
 
@@ -480,7 +482,7 @@ Multimodal Embedding
 
   * - Architecture
     - Models
-    - Inputs
+    - Inputs\*
     - Example HF Models
     - :ref:`LoRA <lora>`
     - :ref:`PP <distributed_serving>`
@@ -492,11 +494,14 @@ Multimodal Embedding
     - ✅︎
   * - :code:`Phi3VForCausalLM`
     - Phi-3-Vision-based
-    - T / I / T + I
+    - T + I
     - :code:`TIGER-Lab/VLM2Vec-Full`
     - 🚧
     - ✅︎
 
+| \*Any combination of modalities joined by :code:`+` are supported. For example, :code:`T + I` means that the model supports text-only, image-only, and text-with-image inputs.
+  On the other hand, modalities separated by :code:`/` are mutually exclusive. For example :code:`T / I` means that the model supports text-only and image-only inputs, but not text-with-image inputs.
+
 .. important::
   Some model architectures support both generation and embedding tasks.
   In this case, you have to pass :code:`--task embedding` to run the model in embedding mode.