torch-mlir/test/Conversion/TorchToLinalg
zjgarvey 297c270980
onnx.Resize and aten._interpolate : allow n spatial dims. (#3368)
The old lowering only had logic for 2d (i.e. images). this patch allows
interpolation for n spatial dims, which is required for some 3d vision
models such as

- onnx/models/pytorch-3dunet_vaiq_int8

which successfully compiles and runs with this patch.
2024-05-20 13:35:27 -07:00
..
basic.mlir Drop torch attributes at the end of backend conversion. (#2876) 2024-02-13 14:32:02 -08:00
broadcast.mlir [TorchToLinalg] Improve broadcast lowerings in strict symbolic modes (#2505) 2023-10-05 15:15:26 -04:00
convolution.mlir [MLIR][Torch] Do not convert bias tensor to element type if NoneType (#3072) 2024-04-02 14:19:26 +05:30
elementwise.mlir [torch] Lower `torch.aten.sinh` to `linalg` (#2662) 2023-12-18 09:15:12 -08:00
flatten.mlir Integrate llvm-project at dabdec1001dc368373dd581cf72f37a440873ce3 (#3300) 2024-05-08 14:43:06 -04:00
gridsampler.mlir [onnx] Gridsampler addition of nearest mode (#3320) 2024-05-10 11:42:10 -07:00
pooling.mlir MaxPool1d lowering to linalg (#3295) 2024-05-10 22:05:26 +05:30
resize.mlir onnx.Resize and aten._interpolate : allow n spatial dims. (#3368) 2024-05-20 13:35:27 -07:00
sparse.mlir [torch-mlir][sparse] recognize to_dense primitive (#3308) 2024-05-08 22:50:17 -07:00
unsqueeze.mlir Integrate llvm-project at dabdec1001dc368373dd581cf72f37a440873ce3 (#3300) 2024-05-08 14:43:06 -04:00
view.mlir [linalg] Implement strict mode lowering for aten.view. (#3319) 2024-05-10 13:45:50 -07:00
view_strict.mlir [linalg] Implement strict mode lowering for aten.view. (#3319) 2024-05-10 13:45:50 -07:00