diff --git a/tests/models/multimodal/test_tensor_schema.py b/tests/models/multimodal/test_tensor_schema.py
index a4cb1a68833a..92390d8c2f7e 100644
--- a/tests/models/multimodal/test_tensor_schema.py
+++ b/tests/models/multimodal/test_tensor_schema.py
@@ -153,4 +153,4 @@ def test_model_tensor_schema(model_arch: str, vllm_runner: type[VllmRunner],
                     if hasattr(model, method_name):
                         getattr(model, method_name)(**mm_kwargs)
 
-            vllm_model.apply_model(validate_model_input)
+            vllm_model.apply_model(validate_model_input)
\ No newline at end of file
diff --git a/vllm/model_executor/models/llava.py b/vllm/model_executor/models/llava.py
index 89d2817b57e0..4927d6b62c6d 100644
--- a/vllm/model_executor/models/llava.py
+++ b/vllm/model_executor/models/llava.py
@@ -72,8 +72,9 @@ class PixtralHFImagePixelInputs(TensorSchema):
     in which case the data is passed as a list instead of a batched tensor.
     """
     type: Literal["pixel_values_pixtral"] = "pixel_values_pixtral"
-    pixel_values: Annotated[Union[torch.Tensor, list[torch.Tensor]],
-                            TensorShape("bn", "c", "h", "w")]
+    pixel_values: Annotated[
+        Union[torch.Tensor, list[torch.Tensor]],
+        TensorShape("bn", "c", "h", "w", dynamic_dims={"h", "w"})]
 
 
 class LlavaImageEmbeddingInputs(TensorSchema):