[torch.export] RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! #152741 Sign in to view logs Summary Jobs assign Run details Usage Workflow file Triggered via issue February 25, 2025 19:45 pianpwk commented on #126674 974...
🐛 Describe the bug The exported model failed to do inference on cuda. import torch ep = torch.export.load('retina.pt2') gm = ep.module() gm(torch.rand(1, 3, 800, 1216)) # success gm = ep.module().cuda() gm(torch.rand(1, 3, 800, 1216).cud...
import torchgen.api.ufunc as ufunc File “/home/anupriya/anaconda3/lib/python3.8/site-packages/torchgen/api/ufunc.py”, line 11, in import torchgen.api.types as api_types File “/home/anupriya/anaconda3/lib/python3.8/site-packages/torchgen/api/types/init.py”, line 1, in from .types...
x = x.cuda() # forward pass with torch.no_grad(): y, feature = net(x) # make score and link map score_text = y[0,:,:,0].cpu().data.numpy() score_link = y[0,:,:,1].cpu().data.numpy() # refine link if refine_net is not None: with torch.no_grad(): y_refiner =...
你可以尝试将NCCL_P2P_LEVEL设置为0，然后重新运行程序。如果问题仍然存在，建议检查你的CUDA和PyTorch...
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT - TensorRT/examples/dynamo/torch_export_cudagraphs.py at 262c87dab545973fd4a3a6b26a22df11a5fe841f · pytorch/TensorRT
Run onnx export got error: RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same weights trained on GPU, and converted both model and image to cuda device, why this error still happens
grad_fn=<ViewBackward>)), scores: tensor([], device='cuda:0', grad_fn=<IndexBackward>), pred_classes: tensor([], device='cuda:0', dtype=torch.int64), pred_masks: tensor([], device='cuda:0', size=(tensor(0), tensor(800), tensor(800)), ...
Tensors and Dynamic neural networks in Python with strong GPU acceleration - `torch._export.aot_compile` CUDA version not compatible with C++ ABI · pytorch/pytorch@a1ba8e6
Tensors and Dynamic neural networks in Python with strong GPU acceleration - `torch._export.aot_compile` CUDA version not compatible with C++ ABI · pytorch/pytorch@de159f0