TensorRT

TensorRT copied to clipboard

# Description Cherry pick of https://github.com/pytorch/TensorRT/pull/2709. Credits to @gcuendet Fixes # (issue) ## Type of change Please delete options that are not relevant and/or add your own. - Bug fix...

peri044

# Description Add aten.topk implementation ## Type of change Please delete options that are not relevant and/or add your own. - New feature (non-breaking change which adds functionality) # Checklist:...

lanluo-nvidia

# Description Cherry pick of https://github.com/pytorch/TensorRT/pull/2796 Fixes # (issue) ## Type of change Please delete options that are not relevant and/or add your own. - Bug fix (non-breaking change which...

peri044

🐛 [Bug] Unable to freeze tensor of type Int64/Float64 into constant layer

4

## Unable to freeze tensor of type Int64/Float64 into constant layer, try to compile model with truncate_long_and_double enabled When I try to test the Transformer Attention layer with tensorRT, I...

supermeng

❓ [Question] How to specific aten operators must be run by LibTorch in C++?

7

## ❓ Question When I compile the SwinTransformer model using Torch-TensorRT, an error appears: ``` terminate called after throwing an instance of 'c10::Error' what(): 0 INTERNAL ASSERT FAILED at "../torch/csrc/jit/ir/alias_analysis.cpp":615,...

demuxin

🐛 [Bug] A Segmentation fault occurs when torchtrt::ts::compile using Torch-TensorRT

3

## Bug Description When I use the code below to compile the touchscript model, a segmentation fault occurs. I compiled the Torch-TensorRT source code with debug mode, and ran the...

demuxin

apbose

apbose

Add support for `torch.ops.aten.full_like.default`

1

- Converter or lowering pass

gs-olive

# Description Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change....

narendasan