AI & Data Science Deep Learning (Training & Inference)

TensorRT Triton Inference Server - archived Maxine Engage with NVIDIA directly and discuss the latest Maxine technology with a global developer community DIGITS cuDNN Frameworks JAX This area is to discuss how to best use JAX on NVIDIA GPUs - and discuss problems and issues. Feel free to share your experiences or ask questions and NVIDIA engineers are here to support you. Riva NVIDIA Riva is a GPU-accelerated SDK for developing multimodal conversational AI applications that delivers real-time performance on GPUs.

Topic	Replies	Views	Activity
How to directly convert a trained Pytorch model into TensorRT model？There are already. pth files ready after training TensorRT	0	28	January 28, 2023
Simple Riva setup for ASR testing Riva jetson	0	44	January 24, 2023
Enable cpu metrics Riva	5	94	January 27, 2023
Triton Model Navigator failing during "optimize" API TensorRT inference-server-triton	0	31	January 27, 2023
TensorRT EfficientNMS plugin FP16 inconsistent(but valid) results TensorRT tensorrt	2	71	January 27, 2023
TRT engine file bigger than original Darknet YOLO V3 model TensorRT tensorrt , deepstream	2	53	January 27, 2023
Maxine and Zoom Maxine maxine	0	37	January 27, 2023
Run YOLOv5 in Deepstream with .engine generated alternatively TensorRT tensorrt , jetson-inference	0	44	January 26, 2023
Inference time increases in for loop cuDNN tensorrt , jetson-inference , yolo , python	0	34	January 27, 2023
Error while loading shared libraries: libnvinfer.so.7: cannot open shared object file: No such file or directory TensorRT	3	5921	January 27, 2023
Application will be correcting they pronunciations and they speech will be clear Riva	2	68	January 27, 2023
Problems running TTS Es Multispeaker FastPitch HiFiGAN in RIVA Riva	5	121	January 27, 2023
Riva_server fails if not all Triton models are loaded Riva	6	208	January 27, 2023
RIVA error, when deploying official Conformer ASR network Riva riva	10	812	January 27, 2023
Successfully deployed Riva to Docker image on local machine via WSL and CUDA Riva	1	45	January 27, 2023
Resize incompatibility when generating a full TensorRT engine for DLA TensorRT tensorrt , dla	2	52	January 26, 2023
Format specification of .trt / .engine? TensorRT	1	40	January 26, 2023
How to train a CNN for custom object detection an use in Jetson nano? cuDNN camera , opencv , cuda , tensorflow , python	0	41	January 26, 2023
Host two or more Nvflare servers in the same physical workstation TensorRT python	1	37	January 26, 2023
Libnvdla_compiler.so: cannot open shared object file: No such file or directory TensorRT	0	32	January 26, 2023
Trtexec cannot convert QAT onnx model to trt model TensorRT tensorrt	7	173	January 26, 2023
Multiple tensorrt engine contexts for different models TensorRT	0	42	January 26, 2023
Int8 is 30% slower than fp16 in cudnn_samples_v8/conv_sample cuDNN	3	159	January 25, 2023
Fine Tune the hind Nvidia Nemo Riva inception	25	263	January 25, 2023
TensorRT INT8 engine calibration cache TensorRT tensorrt , calibration	1	85	January 25, 2023
My TF-TRT converted saved_model gets warning ans slow inferenece TensorRT tensorrt	3	116	January 25, 2023
Unable to verify cuDNN installation on linux (ubuntu 20.04) cuDNN cuda , ubuntu	10	2393	January 25, 2023
Problems with 4090, CUDA (samples), cuDNN (sample). Are these expected? cuDNN tensorrt , cuda	3	617	January 25, 2023
Installing cuDNN cuDNN cuda	5	515	January 25, 2023
Windows CUDNN installation instructions are incompatible with Tensorflow (at least version 2.10) cuDNN	1	91	January 25, 2023