Issues
- 0
- 1
🐛 [Bug] Implement dynamic batch and dynamic shapes support for layer norm converter
#2748 opened by peri044 - 2
🐛 [Bug] `aten.scatter.value` converter error
#2865 opened by HolyWu - 0
`aten.resize_`
#2872 opened by chohk88 - 0
`aten.diagonal`
#2873 opened by chohk88 - 1
- 0
↔ [Converter] Add support for aten.diagonal
#2846 opened by apbose - 0
`aten._local_scalar_dense`
#2743 opened by chohk88 - 4
- 0
aten.atan2.out
#2828 opened by chohk88 - 2
🐛 [Bug] A Segmentation fault occurs when torchtrt::ts::compile using Torch-TensorRT
#2842 opened by demuxin - 7
- 4
🐛 [Bug] error: backend='torch_tensorrt' raised: TypeError: pybind11::init(): factory function returned nullptr
#2827 opened by geraldstanje - 1
🐛 [Bug] failed to install torch-tensorrt
#2825 opened by geraldstanje - 2
🐛 [Bug] torch.export fails to export embedding_bag_aten layer in a standalone test
#2843 opened by peri044 - 1
`aten.log1p`
#2760 opened by gs-olive - 0
Remove `ShapeProp` Pass
#2839 opened by gs-olive - 0
Add support for `torch.ops.aten.full_like.default`
#2838 opened by gs-olive - 0
Add support for `torch.ops.aten.baddbmm.default`
#2837 opened by gs-olive - 0
🐛 [Bug] Llama-2-7b on a 4090 GPU
#2836 opened by gs-olive - 6
❓ [Question] How to solve this warning: Detected this engine is being instantitated in a multi-GPU system with multi-device safe mode disabled.
#2813 opened by demuxin - 0
- 3
🐛 [Bug] `torch.export.load` fails to load file saved with `torch_tensorrt.save` in PyTorch 2.4.0.dev
#2791 opened by HolyWu - 1
- 5
🐛 [Bug] Exporting `OptimizedModule` compiled model
#2742 opened by AvivSham - 2
🐛 [Bug] RuntimeError: [Error thrown at core/util/trt_util.cpp:320] Expected type to be true but got false
#2815 opened by zewenli98 - 2
🐛 [Bug] Nightly import fails
#2820 opened by laikhtewari - 0
🐛 [Bug] Remove CUDNN dependency in the documentation
#2795 opened by zewenli98 - 0
✨[Feature] Autogen TRT Plugins
#2817 opened by narendasan - 0
🐛 [Bug] FAILED conversion\test_rand_aten.py
#2808 opened by zewenli98 - 0
✨[Feature] Handling Scalar type outputs on the boundry between TensorRT and PyTorch subgraphs
#2810 opened by narendasan - 1
- 1
Convert torchscript model to tensorrt
#2798 opened by pengxin233 - 0
🐛 [Bug] torch.where doesn't handle dynamic shapes
#2801 opened by peri044 - 2
🐛 [Bug] SpecViolationError: Node.meta _to_copy_default is missing val field when using unsqueeze
#2799 opened by airalcorn2 - 0
🐛 [Bug] Failures in test_dyn_models.py
#2794 opened by zewenli98 - 0
🐛 [Bug] Example notebook qat-ptq-workflow yields a calibration error failure
#2777 opened by choosehappy - 0
🐛 [Bug] test_bert_base_uncased in TS fails with schema not found error on main
#2783 opened by peri044 - 1
🐛 [Bug] AttributeError: 'TRTPartitioner' object has no attribute '_return_tuple'
#2772 opened by zewenli98 - 1
🐛 [Bug] AttributeError: '_OpNamespace' 'tensorrt' object has no attribute 'SERIALIZED_RT_DEVICE_DELIM'
#2771 opened by zewenli98 - 2
❓ [Question] How should the CMakeLists look like for running .ts files in C++?
#2759 opened by DmytroIvakhnenkov - 0
🐛 [Bug] test_python_runtime is flaky
#2765 opened by peri044 - 2
🐛 [Bug] export and save
#2741 opened by zhongqiu1245 - 1
`aten.empty_strided`
#2758 opened by chohk88 - 1
`aten.sym_storage_offset`
#2757 opened by chohk88 - 0
Associate any output type information with converter instead of hardcoded into TRTInterpreter
#2754 opened by narendasan - 4
🐛 [Bug] RuntimeError: [Error thrown at core/runtime/execute_engine.cpp:132] Expected inputs[i].is_cuda() to be true but got false Expected input tensors to have device cuda, found device cpu
#2744 opened by airalcorn2 - 0
↔ [Converter] Add support for `aten.masked_select.default` in the Dynamo path
#2747 opened by gs-olive - 0
`aten.scatter_reduce.two`
#2739 opened by apbose - 0
`aten.empty.memory_format`
#2738 opened by apbose