🔴 VLM: compile compatibility (#35724)

* llavas

* add mroe models

* fix `compile_forward` test for all models

* fix copies

* make style

* also doesn't support cache class

* fix some tests

* not copied from

* ci green?

* fix tests

* fix copies

* fix tests

* check with `numel` and remove `item`

* fix copies

* fix copies

* Update src/transformers/models/cohere2/modeling_cohere2.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* opt remove cross attn

* gemma2

* fixup

* fixup

* fix newly added test

* maybe fixed?

* green please?

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

tests/test_modeling_common.py

@@ -4324,10 +4324,6 @@ class ModelTesterMixin:
 
             config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
             inputs_dict = self._prepare_for_class(inputs_dict, model_class)
-            if config.model_type in ["llava", "llava_next", "vipllava", "video_llava"]:
-                self.skipTest(
-                    reason="Llava-like models currently (transformers==4.39.1) requires an attention_mask input"
-                )
             if config.model_type in ["paligemma"]:
                 self.skipTest(
                     "PaliGemma-like models currently (transformers==4.41.0) requires an attention_mask input"
@@ -4778,6 +4774,9 @@ class ModelTesterMixin:
             model = model_class(config).to(device=torch_device, dtype=torch.float32)
             set_model_for_less_flaky_test(model)
 
+            if "position_ids" not in inspect.signature(model.forward).parameters:
+                continue  # this model doesn't accept position ids as input
+
             (
                 input_ids,
                 position_ids,