mirror of https://github.com/llvm/torch-mlir
2ef228328f
Support a lowering for dequantization for per channel tensors from `torch` dialect to a linalg decomposition. Tested via a numerical `torch` test. |
||
---|---|---|
.. | ||
e2e_testing | ||
examples | ||
python | ||
test | ||
tools | ||
CMakeLists.txt |