TensorRT

TensorRT copied to clipboard

``` Traceback (most recent call last): File "/jsdasdet/assets/recipe/mixology-clara-monai-swinunetr__benchmarks-stable-pyt_perf-infer_--h100-pcie-80gb-_-1_gpus-1_bs--1_dld-synthetic_seed-42_-source/benchmark.py", line 372, in CLI(benchmark) │ └ └ File "/usr/local/lib/python3.10/dist-packages/jsonargparse/_cli.py", line 96, in CLI return _run_component(components, cfg_init) │ │ └ Namespace(cfg=Config(model_callable='monai.networks.nets.SwinUNETR', model_device=None, model_args=[],...

chohk88

``` 2024-08-30 23:51:44.645 | ERROR | MainProcess | /usr/local/lib/python3.10/dist-packages/model_navigator/commands/correctness/correctness_script.py:106 - Comparison output output__0 contains NaN 2024-08-30 23:51:45.205 | INFO | MainProcess | /usr/local/lib/python3.10/dist-packages/model_navigator/pipelines/pipeline.py:128 - 1 monai.networks.nets.basic_unet.BasicUNet: Validating model torch on...

chohk88

An error occurred in `aten._native_batch_norm_legit_no_training.default` due to mismatched shift weights and invalid output shape computation during Torch-TRT compilation. ``` 2024-08-30 23:23:57.723 | ERROR | Process-5 | /usr/local/lib/python3.10/dist-packages/torch_tensorrt/logging.py:24 - Error Code:...

chohk88

In `torch_tensorrt/dynamo/_compiler.py` requires_full_compilation is not passed to `partitioning.fast_partition` or `partitioning.global_partition`

apbose

## Bug Description model with dynamic shape saved successfully, when load it throw the error ## To Reproduce Steps to reproduce the behavior: test code to reproduce: ``` import torch...

lanluo-nvidia

❓ [Question] torchscript int8 quantization degradation in recent versions

1

TS INT8 degradation later versions Hi all, I get a degradation in results after an INT8 quantization with torchscript, after updating my torch_tensorrt, torch and tensorrt versions. I have listed...

seymurkafkas

## Tasks - [ ] `torch_tensorrt.dynamo.conversion.impl.slice.ops.repeat` - Reference: https://github.com/pytorch/TensorRT/blob/fa02fd3e3a85a6042d11a00cd386f6b69c1d6c4b/py/torch_tensorrt/dynamo/conversion/impl/slice/ops.py#L219-L324 - [ ] `torch_tensorrt.dynamo.conversion.aten_ops_converters.aten_ops_repeat` https://github.com/pytorch/TensorRT/blob/fa02fd3e3a85a6042d11a00cd386f6b69c1d6c4b/py/torch_tensorrt/dynamo/conversion/aten_ops_converters.py#L1152-L1172 - [ ] Unit test, [example: expand](https://github.com/pytorch/TensorRT/blob/main/tests/py/dynamo/conversion/test_expand_aten.py)

dgcnz

🐛 [Bug] The example of torch tensorrt cannot generate images correctly

4

## Bug Description The example of pytorch tensorrt cannot generate images correctly. There were no issues with version v2.3.0, but version v2.4.0 cannot generate images correctly. https://github.com/pytorch/TensorRT/blob/main/examples/dynamo/torch_compile_stable_diffusion.py ## To Reproduce...

pangyoki

remove torchvision as dependency

4

# 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....

lanluo-nvidia

apbose