mirror of https://github.com/llvm/torch-mlir
5227d52c26
This vastly simplifies our code, allowing deleting multiple ops, simplifying multiple passes, and removing a whole pass. Now `refback` dialect is down to one op (refback.alloc_memref, which simplifies allocations to just take a shape instead of individual extents). |
||
---|---|---|
.. | ||
ATen | ||
Basicpy | ||
Numpy | ||
Refback | ||
Refbackrt | ||
TCF | ||
TCP | ||
Torch | ||
CMakeLists.txt |