Alex Chiang

Refine Mod CPU implement

2

The Cytnx arithmetic implementation contained lots duplicated code across different type combinations, which caused: - Difficult maintenance when updating logic - Low code readability due to repetitive patterns This PR...

Unable to compile PyTorch quantized models with torch-mlir due to CustomClass

4

## What happened? I'm trying to convert a quantized ResNet-50 model (using PyTorch's quantization-aware training) to MLIR format, but I'm encountering an error when torch-mlir attempts to import the model....