mirror of https://github.com/llvm/torch-mlir
d466d5b809
Register `aten.fake_quantize_per_channel_affine` and `aten.fake_quantize_per_tensor_affine.tensor_qparams` ops --------- Co-authored-by: Ze Zhang <ze.zhang@getcruise.com> |
||
---|---|---|
.. | ||
test | ||
torch_mlir | ||
torch_mlir_e2e_test | ||
CMakeLists.txt |