mirror of https://github.com/llvm/torch-mlir
9a6fe58a02
- This PR adds new (and equivalent) more tensorized impl of MelWeightMatrix which lowers all the way to linalg. - [Ref Pytorch Impl](https://gist.github.com/PhaneeshB/4e6dfcded3007b1b686fbe28f07a67cd) - Thanks to @rsuderman for pointing out the difficulties [earlier impl](#3503) posed during lowering to linalg and also for providing a better numpy impl 🙏 |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| DefaultDomainAtoF.cpp | ||
| DefaultDomainGtoP.cpp | ||
| DefaultDomainQtoZ.cpp | ||
| OnnxRecurrentLayerOpExpanders.cpp | ||
| PassDetail.h | ||
| Passes.cpp | ||
| Patterns.cpp | ||
| TorchOnnxToTorch.cpp | ||
| Utils.cpp | ||