TensorRT

Topic	Replies	Views	Activity
TensorRT 8.2 and Framework Integrations are out now! tensorrt The latest release of TensorRT, 8.2 GA, and TensorRT Integrations for PyTorch and TensorFlow, is now available for download. Highlight includes: TensorRT 8.2 Optimizations for T5 and GPT-2 deliver real time translati…	4	3184	October 4, 2022
Best practices for reporting an issue or bug relating to TensorRT	0	6734	September 21, 2018
Tensorrt engine combining the output dimentions to (196608,0) instead (1, 256, 384, 2) tensorrt , python , cuda	1	40	June 2, 2023
Is it safe to deallocate nvinfer1::IRuntime after creating an nvinfer1::ICudaEngine but before running inference with said ICudaEngine tensorrt	0	18	June 2, 2023
Trtexec multi-source (streams) and multi-batch performance test failed	2	29	June 2, 2023
How to convert uff model to onnx format tensorrt , onnx	5	110	June 2, 2023
Configuring multiple versions of TensorRT and Tensorflow on HPC share cluster; TF-TRT Warning: Cannot dlopen some TensorRT libraries	7	3146	June 1, 2023
Need help for Nvidia Dali inference-server-triton	1	77	June 1, 2023
Are there binary utilities for TensorRT Engine?	9	365	May 31, 2023
Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[668...Mul_497] tensorrt , nvbugs , onnx	3	345	May 31, 2023
Different FP16 inference behavior on four GPUs	2	171	May 30, 2023
Nsight error:target application exited before profiling started nsight	1	86	May 30, 2023
How to get file profile.metadata.json to use TRT engine explorer?	0	43	May 30, 2023
Could not load dynamic library 'libnvinfer.so.7' cuda , python , tensorrt	1	68	May 30, 2023
Failure to convert torch.nn.functional.grid_sample to TensorRT engine tensorrt , pytorch	4	117	May 30, 2023
Conversion error of Mask RCNN ONNX model for different types weights pytorch , onnx , jetson , tensorrt	5	243	May 30, 2023
Trtexec Error: only activation types allowed as input to this layer tensorrt	5	118	May 30, 2023
TensorRT-8.6.1 (GA): aarch64 sbsa packages contain x86-64 stub libraries tensorrt	2	88	May 29, 2023
TensorRT is slower than pth onnx	1	74	May 29, 2023
Why does Int8 quantization occupy more GPU graphics memory than float16, TensorRT quantization	0	57	May 29, 2023
TensorRT is slower than pth	1	80	May 29, 2023
TRT Pose Model integration with a REST API in python opencv , python	1	76	May 25, 2023
Getting error for tensorrt module not found tf-trt , tensorrt , deepstream	3	106	May 29, 2023
Trying to convert Detectron2's keypoint_rcnn_R_50_fpn_3x to TensorRT tensorrt , onnx	2	106	May 26, 2023
Does TensorRT suport dropout?	1	104	May 24, 2023
How does TensorRT use host memory (RAM) at runtime? onnx , tensorrt	0	102	May 22, 2023
pycuda._driver.MemoryError: cuMemHostAlloc failed: out of memory YOLOv7	1	111	May 25, 2023
Converted model is broken if half precision with dynamic batch size and batch size is greater than 1	7	937	May 29, 2023
TensorRT CUDA 11.x availability for SBSA systems tensorrt	1	81	May 27, 2023
What causes the deserializeCudaEngine() fail and how to get the error message? tensorrt	8	209	May 27, 2023

TensorRT 8.2 and Framework Integrations are out now!

tensorrt

The latest release of TensorRT, 8.2 GA, and TensorRT Integrations for PyTorch and TensorFlow, is now available for download. Highlight includes: TensorRT 8.2 Optimizations for T5 and GPT-2 deliver real time translati…