🔴 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/llava_next/test_modeling_llava_next.py

@@ -365,22 +365,6 @@ class LlavaNextForConditionalGenerationModelTest(ModelTesterMixin, GenerationTes
     def test_training_gradient_checkpointing_use_reentrant_false(self):
         pass
 
-    @unittest.skip(reason="Feedforward chunking is not yet supported")
-    def test_feed_forward_chunking(self):
-        pass
-
-    @unittest.skip(reason="CPU offload is not yet supported")
-    def test_cpu_offload(self):
-        pass
-
-    @unittest.skip(reason="Compile not yet supported because in LLava models")
-    def test_sdpa_can_compile_dynamic(self):
-        pass
-
-    @unittest.skip(reason="Compile not yet supported because in LLava models")
-    def test_sdpa_can_dispatch_on_flash(self):
-        pass
-
     @unittest.skip("FlashAttention only support fp16 and bf16 data type")
     def test_flash_attn_2_fp32_ln(self):
         pass
@@ -391,6 +375,10 @@ class LlavaNextForConditionalGenerationModelTest(ModelTesterMixin, GenerationTes
     def test_flash_attention_2_padding_matches_padding_free_with_position_ids(self):
         pass
 
+    @unittest.skip("LLaVA Next has dynamic control flow in unpadding")
+    def test_generate_compile_model_forward(self):
+        pass
+
 
 @require_torch
 class LlavaNextForConditionalGenerationIntegrationTest(unittest.TestCase):