mirror of https://github.com/llvm/torch-mlir
72349f7522
I spent a little while debugging numerics issues with some tests similar to the ones in quantized_models.py, only to find that pytorch's quantized conv transpose is catastrophically inaccurate. I'll upstream the issue and only leave the tests here which are of the form quantize -> dequantize -> op. |
||
|---|---|---|
| .. | ||
| TorchConversionToMLProgram | ||
| TorchOnnxToTorch | ||
| TorchToArith | ||
| TorchToLinalg | ||
| TorchToSCF | ||
| TorchToStablehlo | ||
| TorchToTMTensor | ||
| TorchToTensor | ||
| TorchToTosa | ||
| Utils | ||
| CMakeLists.txt | ||
| PassDetail.h | ||
| Passes.cpp | ||