mirror of https://github.com/llvm/torch-mlir
c19fc9ba47
Two e2e tests (AdaptiveAveragePool1/2dUnitOutputSizeDynamic) were failing due to numerics. This was as a result of passing -1 as the kernel size in the lowering for the corresponding onnx op GlobalAveragePool. |
||
---|---|---|
.. | ||
jit_ir_common | ||
ltc | ||
onnx_c_importer | ||
pt1 | ||
CMakeLists.txt |