Rob Suderman 60bf6c25af [onnx] Lower `onnx.QLinearMatMul` lowering to `torch` operators (#2776) ... We can plumb the linear matmul into pytorch using its quantized types with side channel information. To handle the final int8 operation we dequantize and requantize.		2024-01-24 12:28:48 -08:00
..
CAPI	Re-organize project structure to separate PyTorch dependencies from core project. (#2542)	2023-11-02 19:45:55 -07:00
Conversion	[onnx] Lower `onnx.QLinearMatMul` lowering to `torch` operators (#2776)	2024-01-24 12:28:48 -08:00
Dialect	AtenAdaptiveMaxPool2d Conversion to Linalg (#2779)	2024-01-24 09:09:56 -08:00
RefBackend	[TorchToLinalg] Lower aten.cat to tensor.concat (#2650)	2023-12-15 15:45:32 -05:00
CMakeLists.txt	Initial TorchOnnxToTorch conversion pipeline. (#2585)	2023-11-21 21:02:55 -08:00
InitAll.cpp	Initial TorchOnnxToTorch conversion pipeline. (#2585)	2023-11-21 21:02:55 -08:00