optimum/exporters/executorch/tasks/causal_lm.py (4 lines):
	- line 93: # TODO: Move quantization recipe out for better composability.
	- line 94: # TODO: Should switch to `TorchAoConfig` once the quant issue on final lm_head layer is fixed.
	- line 98: # TODO: Update torchao to use 0.11.0 once released
	- line 112: # TODO: Should switch to `AOPerModuleConfig` once fix for tied weights is available.


optimum/executorch/attentions/custom_kv_cache.py (1 line):
	- line 340: # TODO: Add replace_cache to exported module


optimum/executorch/modeling.py (1 line):
	- line 690: # TODO: We can remove this block once the executorch runtime supports `cache_position`.