[Bugfix] Fix PixtralHFImagePixelInputs dynamic shape check (vllm-project#22827)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Xiao Yu <xiao.yu@amd.com>

Author: Isotr0py

tests/models/multimodal/test_tensor_schema.py

@@ -153,4 +153,4 @@ def validate_model_input(model):
                     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)

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):