mirror of https://github.com/llvm/torch-mlir
f6f890520b
This includes custom op matching for decomposed operations and fusing dequantization into dense operations. As a validation we compare to the dequant+mm torch implementation. |
||
---|---|---|
.. | ||
e2e_testing | ||
examples | ||
python | ||
test | ||
tools | ||
CMakeLists.txt |