llvm
/
torch-mlir
mirror of https://github.com/llvm/torch-mlir
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
torch-mlir/e2e_testing/torchscript
History
Ramiro Leal-Cavazos e6675a50d3 Add support for dtype argument in reduction ops 
Many reduction ops take as an argument an optional output dtype that
can change the type of the input tensor before the reduction is
performed. This commit adds support for the optional dtype flag that
had been previously ignored.

Test:
/tools/torchscript_e2e_test.sh -f 'ReduceSumDtype'
/tools/torchscript_e2e_test.sh -f 'ReduceSumDImIntListDtype'
 		2021-11-30 12:53:59 -05:00
..
argmax.py add argmax lowering 2021-10-13 14:31:16 -04:00
backprop.py Add e2e test for aten.log_softmax_back_data op 2021-11-19 00:08:28 +05:30
basic.py Add aten.fill.Scalar op lowering 2021-11-30 21:12:15 +05:30
batchnorm.py E2e support for layernorm. 2021-10-04 14:15:13 -04:00
conv.py Dual license the torch-mlir project. 2021-10-01 10:46:08 -07:00
elementwise.py aten.abs and aten.reciprocal to linalg 2021-11-30 11:31:55 -05:00
main.py [MLIR][TORCH] Add E2E support for `aten.squeeze` op 2021-11-30 23:00:28 +05:30
matmul.py Add lowering of aten.matmul op. 2021-10-26 12:45:09 -04:00
mlp.py Support aten::linear with rank 3 inputs 2021-11-18 22:15:04 +05:30
quantized_models.py Dual license the torch-mlir project. 2021-10-01 10:46:08 -07:00
reduction.py Add support for dtype argument in reduction ops 2021-11-30 12:53:59 -05:00
scalar.py add aten.add.int lowering in TorchToStd 2021-11-29 13:22:50 -05:00
squeeze.py [MLIR][TORCH] Add E2E support for `aten.squeeze` op 2021-11-30 23:00:28 +05:30
type_conversion.py Add convertScalarToDtype helper. 2021-11-08 17:50:52 -05:00
type_promotion.py Add convertScalarToDtype helper. 2021-11-08 17:50:52 -05:00
view.py [MLIR][TORCH] Add E2E support for `torch.aten.view` 2021-10-29 22:33:10 +05:30
vision_models.py Add min/max/clamp support. 2021-10-27 13:29:21 -07:00
xfail_sets.py lowered addcmul and addcdiv to linalg 2021-11-24 17:26:47 -05:00