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> |
||
---|---|---|
.. | ||
jit_ir_common | ||
ltc | ||
onnx_c_importer | ||
pt1 | ||
CMakeLists.txt |