Ziheng Jiang
Ziheng Jiang
I tried to lower a model into torch dialect from torch script, but met this error: ``` torch_mlir.compiler_utils.TorchMlirCompilerError: Lowering TorchScript IR -> Torch Backend IR failed with the following diagnostics:...
Hello everyone, we are from the AML (Applied Machine Learning) team at Bytedance. While the TorchMLIR project provides a set of MLIR dialect for Torch, which bridges PyTorch and MLIR...
# Motivation To run a deep learning model, the mainstream approach in TVM is to do code generation with an auto-tuner, which make the performance optimization process easier for developers...
According to the development guidelines(https://github.com/octoml/relax/wiki/Relax-development-guidelines) proposed in the last open source meeting, we agree to improve the codebase quality with better error message and testing. I browsed the current codebase...
We have lots of implicit agreement on variable naming, for example: - `lv` means local variable, while `gv` means global variable - `sh` means shape variable - `storage` means storage,...