Zero Zeng comments

Results 581 comments of


                                            Zero Zeng

ERROR: Could not build wheels for tensorrt, which is required to install pyproject.toml-based projects

I believe we don't support install the python binding with pip on windows. @pranavm-nvidia not sure if we support it today.

Segmentation Fault failure of TensorRT 8.6.1 when converting onnx on GPU GeForce RTX 3050 Ti

I didn't reproduce the issue on TRT 8.6 and 9.2. Could you please: 1. try converting it in our official tensorrt container? 2. try trt 9.2/9.3 Thanks!

Segmentation Fault failure of TensorRT 8.6.1 when converting onnx on GPU GeForce RTX 3050 Ti

``` [02/24/2024-15:17:52] [I] Latency: min = 0.954285 ms, max = 1.15598 ms, mean = 0.957755 ms, median = 0.95752 ms, percentile(90%) = 0.959534 ms, percentile(95%) = 0.960541 ms, percentile(99%) =...

Bus Error failure of TensorRT 8.5 when running sample_onnx_mnist on GPU 3060 laptop.

Bus error looks like an env issue. I don't know how well we support wsl2. @nvpohanh for viz.

How to implement a tensorrt plugin for "Unique" op?

Currently we don't support data dependent plugin. @samurdhikaru for viz.

[castLayer.cpp::validate::33] Error Code 2: Internal Error (Assertion !mOutputTypes.at(0).hasValue() || mOutputTypes.at(0).value() == params.toType failed. )

Looks like you set layer precision constrain which violate the cast(which force precision) Does it work if you run `trtexec --onnx=folded.onnx --fp16 --int8`?

[castLayer.cpp::validate::33] Error Code 2: Internal Error (Assertion !mOutputTypes.at(0).hasValue() || mOutputTypes.at(0).value() == params.toType failed. )

Update: fix typo Another suggestion is to check the cast layer in your model.

[castLayer.cpp::validate::33] Error Code 2: Internal Error (Assertion !mOutputTypes.at(0).hasValue() || mOutputTypes.at(0).value() == params.toType failed. )

> so you mean remove `--precisionConstraints=prefer --layerPrecisions=*:fp16,*:fp32 --layerOutputTypes=*:fp16,*:fp32 `? @nvpohanh do we support usage like this? `*:fp16,*:fp32`

[castLayer.cpp::validate::33] Error Code 2: Internal Error (Assertion !mOutputTypes.at(0).hasValue() || mOutputTypes.at(0).value() == params.toType failed. )

> How do I inpsect the case layer? What shall I look for? Use netron.

[castLayer.cpp::validate::33] Error Code 2: Internal Error (Assertion !mOutputTypes.at(0).hasValue() || mOutputTypes.at(0).value() == params.toType failed. )

Does it work if you run without `--precisionConstraints=prefer --layerPrecisions=*:fp16,*:fp32 --layerOutputTypes=*:fp16,*:fp32`?