torch-mlir/lib
Ramiro Leal-Cavazos 51e267aa37
Combine maximize-value-semantics rewrite patterns into one pattern (#642)
This commit replaces the two rewrite patterns of
maximize-value-semantics with a single pattern that captures the
behavior of both as well as other edge cases previously not
supported. The new pattern works by first performing alias analysis on
a subgraph to see if pattern is applicable, then rewriting all
non-value tensors to value tensors in a single go.
2022-03-10 09:36:52 -08:00
..
CAPI [Torch][Linalg] Add basic support for RNG 2022-01-31 18:56:42 -05:00
Conversion [MLIR][TORCH] Add E2E support for aten.erf op. 2022-03-09 22:22:03 +05:30
Dialect Combine maximize-value-semantics rewrite patterns into one pattern (#642) 2022-03-10 09:36:52 -08:00
RefBackend LLVM bump 2022-02-16 15:28:13 -05:00
CMakeLists.txt Add TMTensor dialect to torch-mlir 2022-02-15 16:45:38 -05:00
InitAll.cpp Add TMTensor dialect to torch-mlir 2022-02-15 16:45:38 -05:00