Rob Suderman f6f890520b [torch][quant] Quantized `torch.mm` for linalg with end-to-end test (#2750) ... This includes custom op matching for decomposed operations and fusing dequantization into dense operations. As a validation we compare to the dequant+mm torch implementation.		2024-01-24 14:02:50 -08:00
..
test	Breakup python pytorch deps (#2582)	2023-11-19 12:10:19 -08:00
torch_mlir	AtenAdaptiveMaxPool2d Conversion to Linalg (#2779)	2024-01-24 09:09:56 -08:00
torch_mlir_e2e_test	[torch][quant] Quantized `torch.mm` for linalg with end-to-end test (#2750)	2024-01-24 14:02:50 -08:00
CMakeLists.txt	Upstream the ONNX importer. (#2636)	2023-12-12 19:02:51 -08:00