Aart Bik 491f4820f5 [torch-mlir][sparse] pre-pend named buffers to parameter list (#3178) ... weights and biases and other model parameters appear as a separate data structure to the traced graph, but are needed when running the MLIR compiled code; this PR implements that extended functionality		2024-04-17 14:44:05 -07:00
..
fx_importer	[torch-mlir][sparse] pre-pend named buffers to parameter list (#3178)	2024-04-17 14:44:05 -07:00
onnx_importer	[onnx] Import `onnx` import to pass remaining tests (#2951)	2024-02-28 12:18:02 -08:00
compile.py	Rename torch_mlir.compile APIs and introduce FX based analogs (#2842)	2024-02-06 19:07:59 -08:00
lit.local.cfg	Upstream the ONNX importer. (#2636)	2023-12-12 19:02:51 -08:00