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. |
||
---|---|---|
.. | ||
configs | ||
debug | ||
linalg_on_tensors_backends | ||
stablehlo_backends | ||
test_suite | ||
tosa_backends | ||
CMakeLists.txt | ||
__init__.py | ||
annotations.py | ||
framework.py | ||
registry.py | ||
reporting.py | ||
utils.py |