Hi
I was trying to run the notebook on my AWS g7e.2xlarge instance which has RTX Pro 6000 Blackwell Server Edition in us-east-1 but I am having an error in the run inference section where it fails to load the cuda kernel with following errors
[/home/ubuntu/void-model/lib/python3.12/site-packages/torch/cuda/__init__.py:287] UserWarning: NVIDIA RTX PRO 6000 Blackwell Server Edition with CUDA capability sm_120 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_70 sm_75 sm_80 sm_86 sm_90. If you want to use the NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
Let me know if I am doing something wrong or if I have to use a nightly build of pytorch
Note : The notebook works fine in NVIDIA L40S (g6e.xlarge) in us-east-2 . I also installed ffmpeg on the ec2 and ipywidgets via pip to make the notebook work for the samples to run.
Hi
I was trying to run the notebook on my AWS g7e.2xlarge instance which has RTX Pro 6000 Blackwell Server Edition in us-east-1 but I am having an error in the run inference section where it fails to load the cuda kernel with following errors
[/home/ubuntu/void-model/lib/python3.12/site-packages/torch/cuda/__init__.py:287] UserWarning: NVIDIA RTX PRO 6000 Blackwell Server Edition with CUDA capability sm_120 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_70 sm_75 sm_80 sm_86 sm_90. If you want to use the NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.Let me know if I am doing something wrong or if I have to use a nightly build of pytorch
Note : The notebook works fine in NVIDIA L40S (g6e.xlarge) in us-east-2 . I also installed ffmpeg on the ec2 and ipywidgets via pip to make the notebook work for the samples to run.