TensorRT
TensorRT copied to clipboard
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
## Bug Description Models exported with `torch.export.export`, saved, loaded and then compiled with `torch_tensorrt.dynamo.compile` cannot be loaded with `torch.export.load` with error: ``` W0820 14:11:53.628000 139673176707712 torch/fx/experimental/symbolic_shapes.py:4424] s0 is not in...
Dynamic shape chunk
Addresses #3064
## ❓ Question https://github.com/pytorch/TensorRT/pull/3099#issuecomment-2303600863 ## What you have already tried ## Environment > Build information about Torch-TensorRT can be found by turning on debug messages - PyTorch Version (e.g., 1.0):...
I tried installing torch_tensorrt using jetpack 5.0 WORKSPACE script but it did not work for my system which is currently using jetpack 6.0 on the jetson agx orin
**Is your feature request related to a problem? Please describe.** The static case with np.full_like was reported to be slow. https://github.com/pytorch/TensorRT/pull/3077#issuecomment-2284587055 **Describe the solution you'd like** Convert it to dynamic...
## Bug Description working on the cross-platform compile feature, when I call torch_tensorrt.save(trt_gm, trt_ep_path, inputs=inputs) try to save the model it will error out with RuntimeError: Engine has not been...
## ❓ Question I was preparing to export a TRT model for Mask2Former using the command **optimized_model = torch_tensorrt.compile(model, inputs=imgs, enabled_precisions={torch.half})**, where model is a Mask2Former loaded through mmseg. However,...
❓ [Question] Why does the speed (fps) of torch-tensorrt perform so badly in `torch.multiprocessing`?
## ❓ Question Hello, dear developer: Thank your for your amazing job! Why does the speed (fps) of torch-tensorrt perform so badly in `torch.multiprocessing`? Currently I use `torch.multiprocessing` to create...