mirror of https://github.com/llvm/torch-mlir
5d28549c2c
This is to fold the common pattern from Bert inference like:
```
%111 = torch.prim.NumToTensor.Scalar %110 : !torch.int ->
!torch.vtensor<[],si64>
%112 = torch.aten.Int.Tensor %111 : !torch.vtensor<[],si64> ->
!torch.int
```
|
||
|---|---|---|
| .. | ||
| GlobalizeObjectGraph | ||
| adjust-calling-conventions.mlir | ||
| canonicalize.mlir | ||
| decompose-complex-ops.mlir | ||
| inline-global-slots.mlir | ||
| invalid.mlir | ||
| maximize-value-semantics.mlir | ||
| ops.mlir | ||
| prepare-for-globalize-object-graph.mlir | ||
| promote-types.mlir | ||
| reduce-op-variants-error.mlir | ||
| reduce-op-variants.mlir | ||
| refine-public-return.mlir | ||
| refine-types-branch.mlir | ||
| refine-types.mlir | ||