Results vary across different GPUs

[ZiyaoLi]

Dear users,

We found that in a small amount of test cases (e. g. T1038 in CASP-14), using different GPUs may lead to different output results, sometimes with large variances on the PDB structures and their evaluation metrics. The issue is potentially caused by the kernel-fusion strategies of jax.jit, but we are not sure currently.

We are sorry for the inconvenience, and are working on locating the problem.

As a temporary solution, we suggest using NVIDIA V100 / A100 / 3090Ti for model inference on local machines.

[Zhang038]

Hi, could you please tell me what is the Cuda version you are using, would the cuda version also make a difference? Thanks a lot.

[ZiyaoLi]

The code was tested on CUDA 11.0 (the default setting), and we reckoned in previous experiments that slight differences happened across different CUDA versions.

[Zhang038]

Thank you so much!