QPyTorch
QPyTorch copied to clipboard
Tiiiger
Low Precision Arithmetic Simulation in PyTorch
hi. I am trying to reproduce this [paper](https://proceedings.neurips.cc/paper/2019/file/65fc9fb4897a89789352e211ca2d398f-Paper.pdf) Is there any way to modify qpytorch exponent bias(seems like default is 2^(exp-1)-1)? thanks in advance
When i call `qtorch.quant` i receive message: ``` Traceback (most recent call last): File "/home/.../anaconda3/envs/qtorch/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 1900, in _run_ninja_build `subprocess.run(` File "/home/.../anaconda3/envs/qtorch/lib/python3.10/subprocess.py", line 524, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError:...
When I use Qpytorch, it reports the following error: RuntimeError: Ninja is required to load C++ extensions. However, I have already installed Ninja, how can I solve this problem?
This PR contains the below two changes 1. __forceinline__ needs inline and always_inline on ROCm 2. extra_include_paths is required for the hipification of quant_cuda header files.
