skip one op for coreml partitioner (#2826)

Summary:
Pull Request resolved: #2826

There are some issues with the current two ops in coreml side. While waiting for the fix, skip them for now
```
"aten.index_put.default"
```
test with
```
python3 -m examples.models.llama2.export_llama --coreml --use_kv_cache
```

Reviewed By: mergennachin

Differential Revision: D55680297

fbshipit-source-id: 99225a22b0369583c36fe67709b66b0784a7765d

examples/models/llama2/export_llama_lib.py

@@ -593,7 +593,10 @@ def _export_llama(modelname, args) -> str:  # noqa: C901
         partitioners.append(
             # pyre-ignore: Undefined attribute [16]: Module `executorch.backends` has no attribute `apple`
             CoreMLPartitioner(
-                skip_ops_for_coreml_delegation=None, compile_specs=compile_specs
+                skip_ops_for_coreml_delegation=[
+                    "aten.index_put.default",
+                ],
+                compile_specs=compile_specs,
             )
         )
         modelname = f"coreml_{modelname}"