mirror of https://github.com/llvm/torch-mlir
82a3860e25
This commit makes the following changes needed to update bump LLVM: - Replace `linalg.init_tensor` with `tensor.empty` (see: https://reviews.llvm.org/D135129) - Replace `NoSideEffect` with `Pure` (see https://reviews.llvm.org/D135505) - Replace `body` region accessor for `ReduceOp` and `ReduceWindowOp` with `getBody` - Fix incorrect use of `tosa::ReduceSumOp` in `AtenNativeLayerNormOp` conversion pattern. The result type of `tosa::ReduceSumOp` must have the same rank as the input type. (see: https://www.mlplatform.org/tosa/tosa_spec.html#_reduce_sum) Co-authored-by: Ashay Rane <ashay@users.noreply.github.com> Co-authored-by: Ashay Rane <ashay@users.noreply.github.com> |
||
---|---|---|
.. | ||
include | ||
lib | ||
test | ||
tools | ||
CMakeLists.txt | ||
README.md |
README.md
Torch-MLIR Dialects Project
Sources for torch-mlir's public dialects (containing ops/types/attributes that are unique to Torch-MLIR at the moment)
This project is intended to be used via LLVM's external projects setup:
-DLLVM_EXTERNAL_PROJECTS=torch-mlir-dialects
-DLLVM_EXTERNAL_TORCH_MLIR_DIALECTS_SOURCE_DIR={this_directory}
It depends on the mlir
project.