robotcator

@alexiskattan please do not use this code now, for the bug mentioned in this(https://github.com/longcw/yolo2-pytorch/issues/19)

It seems that converting from a quantization-aware training model to a post-training quantization model is not yet supported by the document. https://nervanasystems.github.io/distiller/algo_quantization.html Is there any plan to do this?

@lindsey98 Hi, you can refer cuda12 branch which add sm90 compiling flag.

can you try this method ? `pip install git+https://github.com/dptech-corp/Uni-Core.git`

The error message shows that `core dumped` on conformer generation, can you check the legality of smiles when using rdkit to generate conformer? Additionally, can you provide the version of...

Hi, `fused_multi_tensor` is cuda kernel in unicore, the warning is said that your version didn't compiled with the correct cuda / pytorch version, If you want to use the cuda...

@lindafei01 what compile option do you used ? If you install it from source, the warning message still raise ?

> I am also trying to install Unicore from the source. I would like to know how to specify the version. Running 'python setup.py install' by default requires torch>=2.0.0. Yes,...

Hi, lucifer, we upload the file in github release, you can download it from [this](https://github.com/dptech-corp/Uni-Core/files/15258412/wikitext-2-v1.zip).

can you check your torch install with cuda version?