remove split and split_with_size from decomp tables

Author: raayandhar

projects/pt1/python/torch_mlir/dynamo.py

@@ -52,8 +52,6 @@ def _get_decomposition_table():
         # support for aten.native_batch_norm_backward.
         aten._native_batch_norm_legit_functional,
         aten.native_group_norm,
-        aten.split.Tensor,
-        aten.split_with_sizes,
         aten.norm.ScalarOpt_dim,
         aten.embedding_dense_backward,
         aten.native_layer_norm_backward,

python/torch_mlir/extras/fx_decomp_util.py

@@ -10,8 +10,6 @@
     torch.ops.aten.norm.ScalarOpt_dim,
     torch.ops.aten.native_group_norm,
     torch.ops.aten.upsample_bilinear2d.vec,
-    torch.ops.aten.split.Tensor,
-    torch.ops.aten.split_with_sizes,
     torch.ops.aten.native_layer_norm,
     torch.ops.aten.masked_fill.Tensor,
     torch.ops.aten.masked_fill.Scalar,