torch-mlir/lib
Rob Suderman e30a083aff
[torch] Rework lowering to tm_tensor.scatter to stop serialization (#2940)
We collapsed and broadcasted scatter indices to a single element
version. We should instead upport `tm_tensor.scatter`s support for
multiple indices and the implicitly broadcasted behavior. This avoids
the serialization and materializing a needlessly large indices tensor.
2024-02-27 11:46:57 -08:00
..
CAPI Clang format refresh (#2812) 2024-01-29 12:59:33 -05:00
Conversion [torch] Rework lowering to tm_tensor.scatter to stop serialization (#2940) 2024-02-27 11:46:57 -08:00
Dialect [torch] Rework lowering to tm_tensor.scatter to stop serialization (#2940) 2024-02-27 11:46:57 -08:00
RefBackend [TorchToLinalg] Lower aten.cat to tensor.concat (#2650) 2023-12-15 15:45:32 -05:00
CMakeLists.txt [Stablehlo] add refbackend (#2712) 2024-02-16 01:08:48 +08:00
InitAll.cpp [Stablehlo] add refbackend (#2712) 2024-02-16 01:08:48 +08:00