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. |
||
---|---|---|
.. | ||
CAPI | ||
Conversion | ||
Dialect | ||
RefBackend | ||
python | ||
CMakeLists.txt | ||
lit.cfg.py | ||
lit.site.cfg.py.in |