torch-mlir

History

Felix Schneider fb21a85874 [TorchToLinalg] Lower grouped conv2d to linalg Op with correct dimension ordering (#2623 ) The linalg Op `linalg.conv_2d_ngchw_fgchw` had a bug where 1. Weights were accessed as G,F,C,H,W instead of as F,G,C,H,W 2. Output was accessed as N,F,G,H,W instead of as N,G,F,H,W Now this has been fixed in https://github.com/llvm/llvm-project/pull/73855 which broke the torch-mlir lowering to that Op. This patch switches lowering in torch-mlir to the newly introduced `linalg.conv_2d_ngchw_gfchw` op which accesses weights in an order that is compatible with PyTorch's memory layout. Fix https://github.com/llvm/torch-mlir/issues/2622	2023-12-08 14:18:23 +01:00
..
main.py	Re-organize project structure to separate PyTorch dependencies from core project. (#2542 )	2023-11-02 19:45:55 -07:00
xfail_sets.py	[TorchToLinalg] Lower grouped conv2d to linalg Op with correct dimension ordering (#2623 )	2023-12-08 14:18:23 +01:00

[TorchToLinalg] Lower grouped conv2d to linalg Op with correct dimension ordering (#2623 )

The linalg Op `linalg.conv_2d_ngchw_fgchw` had a bug where

1. Weights were accessed as G,F,C,H,W instead of as F,G,C,H,W
2. Output was accessed as N,F,G,H,W instead of as N,G,F,H,W

Now this has been fixed in
https://github.com/llvm/llvm-project/pull/73855 which broke the
torch-mlir lowering to that Op.

This patch switches lowering in torch-mlir to the newly introduced
`linalg.conv_2d_ngchw_gfchw` op which accesses weights in an order that
is compatible with PyTorch's memory layout.

Fix https://github.com/llvm/torch-mlir/issues/2622

2023-12-08 14:18:23 +01:00

main.py

Re-organize project structure to separate PyTorch dependencies from core project. (#2542 )

2023-11-02 19:45:55 -07:00

xfail_sets.py

[TorchToLinalg] Lower grouped conv2d to linalg Op with correct dimension ordering (#2623 )

2023-12-08 14:18:23 +01:00