🔴 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/models/emu3/test_modeling_emu3.py

@@ -386,10 +386,6 @@ class Emu3Vision2TextModelTest(ModelTesterMixin, GenerationTesterMixin, Pipeline
     def test_cpu_offload(self):
         pass
 
-    @unittest.skip("Doesn't work, tensors are not almost same")  # TODO raushan fixme
-    def test_custom_4d_attention_mask(self):
-        pass
-
     @unittest.skip("VQ-VAE module doesn't initialize weights properly")
     def test_initialization(self):
         pass