Zero Zeng

I didn't see this option, are you using an old version of polygraphy? ``` --model-type {frozen,keras,ckpt,onnx,engine,uff,trt-network-script,caffe} The type of the input model: {{'frozen': TensorFlow frozen graph; 'keras': Keras model; 'ckpt':...

Okay looks like we need to update the README.

Filed internal MR to fix this.

1. Can you share the onnx and plugin.so here for quick reproduce? 2. Which GPU you are using? also Nvidia Driver version and CUDA version etc. please provide these follow...

If possible please use trtexec to benchmark the TRT performance, a sample command would be like `trtexec --onnx=model.onnx --plugins=./libmmdeploy_tensorrt_ops.so --fp16`

I‘ve requested access.

Check with TRT 8.6(TRT docker 23.10) on A100. the mean gpu time is 102.96ms. So this doesn't looks like the bug in TRT ``` [11/14/2023-11:22:42] [I] H2D Latency: min =...

> Download `nv-tensorrt-local-repo-cross-aarch64-l4t-10.0.1-cuda-12.4_1.0-1_all.deb` at local, then > `sudo dpkg -i install nv-tensorrt-local-repo-cross-aarch64-l4t-10.0.1-cuda-12.4_1.0-1_all.deb` No, `cross-aarch64` is for cross compilation, TRT is bundled with Jetpack on embedded platform for user. Please wait...

Other usage is not verified by QA.

DDS(data-dependent shape) is still under active development and there are still some restriction. please check our developer guide and api doc for more information.