[Static Runtime] Use composite op for TE fusion (#74126)

Summary:
Pull Request resolved: #74126

When we perform fusion without the composite op, `TensorExprDynamicGroup`, it ends up not reusing the output tensor buffers. So, until we figure out a way to do that with `TensorExprGroup` op, it seems strictly better to use composite op, even though it involves going to the JIT.
ghstack-source-id: 151191941

Test Plan:
Tested locally with `ptvsc2_predictor_bench` on the Video model.

Performance analysis with `caffe2/caffe2/fb/predictor/bench:limb` on the Video model locally showed an improvement of ~1% with this change.

Reviewed By: mikeiovine

Differential Revision: D34831280

fbshipit-source-id: e523878364b519ccd51b78d52d9f6c9d3e8def17

Author: navahgar

torch/csrc/jit/runtime/static/fusion.cpp

@@ -345,7 +345,7 @@ void performTensorExprFusion(
   FuseTensorExprs(
       traced_graph,
       /*min_group_size*/ 2,
-      /*add_composed_op*/ false,
+      /*add_composed_op*/ true,
       /*fuse_to_dynamic_shapes*/ true);
   inlineFallbackGraphs(traced_graph);
   graph->block()->clear();