Update on "[Executorch][llama] Make RoPE freq calculation broadcast for per head"

This is a workaround, may not be even worth landing, to avoid broadcasting
semantics in the mul op and for that matter any binary op. Current
implementation of oiptimized ops doesnt handle broadcasting and falls back to
portable op implementation.

This diff also fixes an issue where (as seen in llama) two tensors of binary op
are not broadcasting, but they have different # of dims, which results in
invocation of unoptimized path. e.g. a = [1, 1, 2048], b = [2048], out = [1, 1,
2048].

In llama case this is optimized path when generating one token at a time. Not
so during pre-fill

Making optimized op handle broadcasting, and support vectorization, is not
hard, but may take some time.

Differential Revision: [D54766067](https://our.internmc.facebook.com/intern/diff/D54766067/)

[ghstack-poisoned]

Author: kimishpatel

examples/models/llama2/export_llama_lib.py

@@ -22,9 +22,9 @@
 from executorch.backends.xnnpack.partition.xnnpack_partitioner import (
     XnnpackDynamicallyQuantizedPartitioner,
 )
-from executorch.exir.backend.backend_details import CompileSpec
 
 from executorch.examples.models.llama2.llama_transformer import Transformer
+from executorch.exir.backend.backend_details import CompileSpec
 
 from executorch.sdk.etrecord import generate_etrecord
 from executorch.util.activation_memory_profiler import generate_memory_trace