Deep Learning (Training & Inference)   TensorRT


Topic Replies Views Activity
TensorRT 8.0: What’s New

The latest release of high performance deep learning inference SDK, TensorRT 8 GA is now available for download. This version of TensorRT includes: BERT Inference in 1.2 ms with new transformer optimizations Achieve ac…

2 334 July 20, 2021
Best practices for reporting an issue or bug relating to TensorRT
0 3543 September 21, 2018
Segment Fault due to strlen-avx2.S missing
4 62 September 19, 2021
Multiple calls of enqueueV2
15 304 September 19, 2021
Simple 2 layer U-Net breaks TensorRT conversion
4 43 September 18, 2021
LPRNet with TensorRT
2 35 September 17, 2021
Missing quantization data when converting TF2.x QAT => ONNX => TensorRT
tensorrt
2 36 September 17, 2021
TensorRT dynamic shape err: [slot.h::decode::151] Error Code 2: Internal Error (Assertion index < nbSlots failed.invalid encoded reference to a slot)
tensorrt
10 72 September 17, 2021
On tensorRT Build i get this errror " No rule to make target 'nvinfer_LIB_PATH-NOTFOUND"
3 53 September 17, 2021
No cuda capable device detected -every time when i shutdown my server
deep-learning
1 26 September 17, 2021
Mixed precision + kSTRICT_TYPES, which type is chosen?
8 166 September 17, 2021
TensorRT Batching Speed scales poorly
tensorrt ,  cuda
4 52 September 17, 2021
How could I change the batchsize during inference when using a tensorRT model converted by onnx?
7 2299 September 17, 2021
TensorRT and Tensor.js
1 38 September 17, 2021
Latency linearly increases when increased batch size or concurrent models
inference-server-triton
7 64 September 17, 2021
Cannot find any whl file in zip file of TensorRT 8.0.3.4 for windows
tensorrt
2 50 September 16, 2021
Question about TensorRT reproducibility on different architectures
2 59 September 16, 2021
TensorRT engines are built so differently with the same IBuilderConfig, how to fix?
0 34 September 16, 2021
How to pass uint8 input to a tensorrt engine?
3 61 September 16, 2021
[QST] Best practices of handling competence of gpu resource?
tensorrt ,  cuda ,  jetson-inference ,  performance
0 36 September 16, 2021
Bad inference performance of Transformer decoder with incremental decoding
1 38 September 16, 2021
Inference time becomes longer when doing non-continuous fp16 or int8 inference
tensorrt ,  jetson-inference
20 303 September 16, 2021
TensorRT parse onnx failed with AveragePool layer
12 202 September 16, 2021
TensorRT onnx parser + BatchedNMSDynamicPlugin
1 32 September 16, 2021
Guidance for PyTorch to TensorRT Deployment
1 30 September 15, 2021
TensorRT 8 - nvinfer1::CudaRuntimeError GUI application
cuda
3 71 September 15, 2021
CUDA device not detected in Tensorflow
cuda ,  tensorflow ,  ubuntu
1 43 September 15, 2021
Tensorrt is slower than pytorch
2 38 September 15, 2021
How to draw the ROI region of interest on frames using deepstream 5.1 python?
1 22 September 15, 2021
Android for NX module
board-design
1 22 September 15, 2021