erichtho

Sorry, I can't share my code, it's a part of big project. I'm try to simplify it, but can't reproduce the error with simplified code(still trying). Onnx model is transformed...

Yes, it's related to request concurrency. And I feel like it appear with higher opportunity when there are lots of request with almost maximum shape. I checked with top, dmesg,...

Same error. and `nvcc --version` matches `python -c 'import torch; print(torch.version.cuda);'` 

> Same error. and `nvcc --version` matches `python -c 'import torch; print(torch.version.cuda);'`  also found with dmesg:

hi, I downgrade torch to 2.1.2 and resolve the problem(also changed xformers version to [v0.0.23.post1](https://github.com/facebookresearch/xformers/releases/tag/v0.0.23.post1)). here is how I locate problem: 1.debug with pdb, found is torch.nn.Conv3d raise segmentation fault...