Quinn Dawkins 6f81ad7293 [TorchToLinalg] Improve broadcast lowerings in strict symbolic modes (#2505) ... With strict symbolic shapes, we can assume numpy-style dynamic broadcasts never occur. This improves the lowering in the presence of this assumption.		2023-10-05 15:15:26 -04:00
..
TorchConversionToMLProgram	Fix a few missing dependencies. (#2014)	2023-04-11 11:18:49 -07:00
TorchToArith	[Torch Dialect] Add canonicalize pattern for aten.is_floating_point (#2194)	2023-06-07 17:05:31 +08:00
TorchToLinalg	[TorchToLinalg] Improve broadcast lowerings in strict symbolic modes (#2505)	2023-10-05 15:15:26 -04:00
TorchToSCF	update llvm-project to d13da154a7c7eff77df8686b2de1cfdfa7cc7029 (#2483)	2023-09-26 16:15:55 -05:00
TorchToStablehlo	Remove mlir-hlo (replace with stablehlo). (#2460)	2023-09-12 19:10:02 -07:00
TorchToTMTensor	Bump llvm-project to f66cd9e9556a53142a26a5c21a72e21f1579217c. (#2466)	2023-09-19 10:50:53 -07:00
TorchToTosa	Fixing implicit double to float casts. (#2476)	2023-09-20 10:48:40 -07:00
Utils	[MLIR][TORCH] Add support for conversion to int8 dtype	2023-10-02 09:48:46 +05:30
CMakeLists.txt	mhlo: migrate conversion to stablehlo (#1840)	2023-02-02 07:29:47 -06:00
PassDetail.h	Minor fixes for `ConvertTorchConversionToMLProgram`. (#1991)	2023-04-04 09:09:58 -07:00
Passes.cpp	Remove mlir-hlo (replace with stablehlo). (#2460)	2023-09-12 19:10:02 -07:00