TensorRT

TensorRT copied to clipboard

How to accelerate GCN using torch-geometric with TensorRT?

1

runningpp

[FEATURE REQUEST] Support onnx's local function as custom plugin

1

[Functions](https://github.com/gramalingam/onnx/blob/main/docs/IR.md#functions) is a feature in onnx, which can be thought of as an operator combined with an implementation of the operator using other, more primitive, ops, referred to as the...

tp-nan

Fused_MHA does not support when seq_len = 1024, Dh==72, causal_mask==false

1

When I use FMHA_v2, I found it does not support my scenes. So i wonder is there any way to use fmha_v2 except changing model. Thx a lot.

liangzelang

XXX failure of TensorRT X.Y when running XXX on GPU XXX

2

## Description I get this this issue [08/31/2024-21:29:05] [TRT] [I] [MemUsageChange] TensorRT-managed allocation in building engine: CPU +6, GPU +64, now: ## Environment **TensorRT Version**:8.5.2.2 **NVIDIA GPU**:Orin NX **NVIDIA Driver...

eraykstrl

failed to build the serialized network due to the wrong shape inference of the LayerNormalization operator

3

## Description For the following onnx model,  it can be imported by the onnx frontend in TensorRT. However, it failes to build the serialized network. The following error message...

coffezhou

"Internal Error: MyelinCheckException: gvn.cpp:318: CHECK(graph().ssa_validation()) failed." when building engine

1

## Description I encountered the following error when trying to build trt engine from onnx model. ``` 110947: reshape: /Reshape_32 _ /Transpose_17_reshape_output.1-(f16[__mye111018_proxy.1,1,1025,2,801,2][]so[], mem_prop=0) | /Concat_47_output_0' castIn.1-(f16[__mye111018_proxy.1,1,2050,801,2][]so[], mem_prop=0), stream = 0...

xjy1995

Export failure of TensorRT 10.11 when running scaled dot product on GPU A6000

2

I had an export issue for attention layer in a video transformer architecture in tensorrt 10.7 and seemed to be fixed in 10.11. However when I exported using 10.11 on...

evolvingai

Invalid node error when generating model engine using trtexec for onnx model "ESS DNN stereo disparity" from NGC catalog

4

I am trying to generate the model engine from the "ESS DNN stereo disparity" onnx file on my jetson orin nano using trtexec (and tensorrt10.3.0). I am using the model...

arvindrk2

Accuracy problem between onnx and fp16 trt inference

3

## Description I am encountering an accuracy discrepancy between ONNX inference and TensorRT FP32 inference. ## Environment **TensorRT Version**: 10.8.0.43 **NVIDIA GPU**: RTX 3060 **NVIDIA Driver Version**: 560.35.05 **CUDA Version**:...

KexianShen

LSTM model converted to TensorRT is slower than PyTorch on RTX 4090

6

**System Information** * **OS**: Ubuntu 22.04 * **GPU**: NVIDIA RTX 4090 * **TensorRT Version**: 10.11.0.33 * **PyTorch Version**: 2.7.0 * **ONNX Opset**: 14 --- ### 🧠 Problem Summary I converted...

jds250