File tree Expand file tree Collapse file tree 2 files changed +3
-3
lines changed
Expand file tree Collapse file tree 2 files changed +3
-3
lines changed Original file line number Diff line number Diff line change 1616@experimental (
1717 "This API and all of Metal backend related functionality are experimental."
1818)
19- class MetalBackend (BackendDetails , AotiBackend ):
19+ class MetalBackend (AotiBackend , BackendDetails ):
2020 """
2121 MetalBackend is a backend that compiles a model to run on Metal/MPS devices. It uses the AOTInductor compiler to generate
2222 optimized Metal kernels for the model's operators with libtorch-free. The compiled model can be executed on Metal devices
Original file line number Diff line number Diff line change 99
1010import torch
1111from executorch .backends .aoti .aoti_backend import AotiBackend
12- from executorch .exir .backend .backend_details import BackendDetails
1312from executorch .exir ._warnings import experimental
13+ from executorch .exir .backend .backend_details import BackendDetails
1414from torch ._inductor .decomposition import conv1d_to_conv2d
1515
1616
1717@final
1818@experimental (
1919 "This API and all of cuda backend related functionality are experimental."
2020)
21- class CudaBackend (BackendDetails , AotiBackend ):
21+ class CudaBackend (AotiBackend , BackendDetails ):
2222 """
2323 CudaBackend is a backend that compiles a model to run on CUDA devices. It uses the AOTInductor compiler to generate
2424 optimized CUDA kernels for the model's operators with libtorch-free. The compiled model can be executed on CUDA devices
You can’t perform that action at this time.
0 commit comments