NVIDIA-AI-IOT/torch2trt

Issues

• installation of torch2trt for tensorrt=10.8.0.43.py3 -- AttributeError: module 'tensorrt' has no attribute '__version__'

  #953 opened 22 days ago by monajalal
  1

• Update torch2trt to work for tensorrt 10.8

  #954 opened 22 days ago by monajalal
  0

• AttributeError: 'tensorrt_bindings.tensorrt.INetworkDefinition' object has no attribute 'add_convolution'. Did you mean: 'add_convolution_nd'?

  #920 opened a year ago by AWallyAllah
  5

• This project not update for a long time?

  #952 opened 2 months ago by lzcchl
  0

• Issue with Padding Implementation and Torch2TRT Conversion

  #951 opened 2 months ago by korkland
  0

• Inconsistent inference results between PyTorch and converted TensorRT model with AvgPool2d operator

  #905 opened a year ago by hongliyu0716
  1

• AttributeError when using torch.nn.functional.pad

  #936 opened 9 months ago by clementabary
  3

• ValueError: __len__() should return >= 0

  #949 opened 2 months ago by My12123
  0

• There are issues with support for `ConvTranspose2d`

  #946 opened 6 months ago by mortal-Zero
  3

• error while importing

  #948 opened 4 months ago by i80287
  1

• OSS-Fuzz Integration

  #929 opened 9 months ago by ennamarie19
  1

• DEPRECATION: Loading egg at e:\miniconda\lib\site-packages\torch2trt-0.5.0-py3.11.egg is deprecated.

  #947 opened 5 months ago by tangze-Asuka
  0

• Unsupported methods encountered issue, `torch.Tensor.to(torch.device("cuda"))`. Will torch.Tensor.to for devices be implemented?

  #944 opened 7 months ago by darrenchang
  1

• Unsupported method!

  #940 opened 8 months ago by boge2023
  1

• when use own defined convertor, why int tensor input has no _trt attribute?

  #943 opened 7 months ago by lantudou
  2

• Add ProfilingVerbosity Option to Engine Build Configuration

  #942 opened 7 months ago by Houssem-kikleo
  0

• apiVersion: apps/v1 kind: Deployment metadata: name: titan-dataguard spec: replicas: 3 selector: matchLabels: app: titan-dataguard template: metadata: labels: app: titan-dataguard spec: containers: - name: titan-dataguard image: your_docker_image ports: - containerPort: 80 --- apiVersion: v1 kind: Service metadata: name: titan-dataguard spec: selector: app: titan-dataguard ports: - protocol: TCP port: 80 targetPort: 80 type: LoadBalancer

  #941 opened 8 months ago by felipeliliti
  0

• Is that available on orin nano?

  #933 opened 9 months ago by adrenalin7237
  2

• ONNX export mode is set to TrainingMode.EVAL, but operator 'instance_norm' is set to train=True

  #935 opened 8 months ago by edwardnguyen1705
  2

• ROOT CAUSE？when used `nn.Transpose3d `, the shape of weight of transpose3d was consistency with nn.Transpose3D in torch.

  #939 opened 8 months ago by Yuxiang1990
  0

• ROOT CAUSE? `InstanceNorm3D` with tensorRT result consistency with nn.Instance_norm3d

  #938 opened 8 months ago by Yuxiang1990
  0

• Failed to 'sudo python3 setup.py install --plugins'

  #937 opened 9 months ago by CMeiyi
  0

• Inconsistent inference results between PyTorch and converted TensorRT model with BatchNorm or InstanceNorm operator

  #910 opened a year ago by hongliyu0716
  1

• Unable to convert SigLIP text transformer due to missing model input when exporting model to onnx

  #931 opened 9 months ago by aliencaocao
  0

• SyntaxWarning of dataset.py:61

  #930 opened 9 months ago by grapevine-AI
  1

• _trt.shape overflow when converting from pytorch to TRT

  #927 opened 9 months ago by Justin020718
  5

• How to save a model to TRT file? Not covered in the docs

  #928 opened 9 months ago by talcs
  1

• Segmentation fault on nn.Linear

  #924 opened 10 months ago by brazhenko
  1

• There are questions about the parameters needed for forward propagation in model transformation

  #926 opened 10 months ago by huangshilong911
  2

• AttributeError: 'DataParallel' object has no attribute 'img_size'

  #925 opened 10 months ago by huangshilong911
  2

• Package is not PEP 517 compliant, making it incompatible with package managing tools

  #919 opened a year ago by elisa-aleman
  0

• Error in converting hybridnets model using torch2trt

  #918 opened a year ago by moscaAle29
  0

• [Question & FeatureRequest] Is that possible to convert a torch.nn.Module to TRTMoudle?

  #917 opened a year ago by ElinLiu0
  1

• torch2trt shows error when converting a model, even though regular pytorch -> onnx -> tensorrt and inference is successful

  #916 opened a year ago by ninono12345
  0

• python model successfully tested on polygraphy tensorrt, but failed, when loading on torch2trt

  #915 opened a year ago by ninono12345
  0

• 'tensorrt.tensorrt.Builder' object has no attribute 'build_cuda_engine'

  #913 opened a year ago by maxmelichov
  0

• Inconsistent inference results between PyTorch and converted TensorRT model with ConvTranspose2d operator

  #912 opened a year ago by hongliyu0716
  0

• Inconsistent inference results between PyTorch and converted TensorRT model with Interpolate operator

  #911 opened a year ago by hongliyu0716
  0

• Inconsistent inference results between PyTorch and converted TensorRT model with MaxPool2d operator

  #909 opened a year ago by hongliyu0716
  0

• Inconsistent inference results between PyTorch and converted TensorRT model with Selu operator

  #908 opened a year ago by hongliyu0716
  0

• repvggblock in torch2trt

  #907 opened a year ago by chennaikai11
  0

• Inconsistent inference results between PyTorch and converted TensorRT model with Pad operator

  #906 opened a year ago by hongliyu0716
  0

• TypeError: 'int' object is not iterable when using torch2trt to convert a PyTorch model with Transformer operator

  #897 opened a year ago by Thrsu
  1

• Inconsistent inference results between PyTorch and converted TensorRT model using with Linear operator

  #904 opened a year ago by Thrsu
  0

• Inconsistent inference results between PyTorch and converted TensorRT model using with Normalize operator

  #903 opened a year ago by Thrsu
  0

• Inconsistent inference results between PyTorch and converted TensorRT model using with Silu operator

  #902 opened a year ago by Thrsu
  0

• Inconsistent inference results between PyTorch and converted TensorRT model using with Softplus operator

  #901 opened a year ago by Thrsu
  0

• Inconsistent inference results between PyTorch and converted TensorRT model using with LogSoftmax operator

  #900 opened a year ago by Thrsu
  0

• Inconsistent inference results between PyTorch and converted TensorRT model using with GumbelSoftmax operator

  #899 opened a year ago by Thrsu
  0

• torch_dim_to_trt_axes does not handle dim=-1 correctly

  #898 opened a year ago by Thrsu
  0