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…	6	6027	January 10, 2025
Best practices for reporting an issue or bug relating to TensorRT	0	8898	September 21, 2018
PyTorch Vulnerability – No Fixed Version Available for JetPack 5 jetpack , pytorch , jetson	0	3	August 18, 2025
How am I able to make TensorRT work and quantize the AI model to FP4?	3	10	August 18, 2025
TensorFlow container opening Jupyter Server directory in read-only location - Jupyter Lab cannot be used cudnn	3	85	August 14, 2025
TensorRT Cloud Early Access application link broken tensorrt	2	21	August 14, 2025
Converting an ONNX model to TensortRT Engine Takes Days cudnn , cublas	1	21	August 14, 2025
"Unable to Claim Certificate for Generative AI Explained Course" cudnn	1	14	August 13, 2025
Long Cuda Synchronization times in TensorRT inference (Python API) tensorrt , cuda , python , cudnn	0	12	August 11, 2025
Can I do onnx (fixed batch size) to TRT (dynamic batch size) conversion?	3	23	August 11, 2025
TensorRT 10.4 inference gives incorrect results (correct when using v8.6) tensorrt , cudnn	1	83	August 11, 2025
Edit Onnx layer name using onnx grpah surgeon cause TensorRT to report anassertion on Conv layer during onnx parsing	4	26	August 11, 2025
FP16/ FP8 Training Stability — What’s Working and What’s Failing? mixed-precision , training	1	25	August 10, 2025
Tensorrt installation problem cudnn	0	16	August 7, 2025
Documentation inconsistency: setOptimizationLevel vs setBuilderOptimizationLevel API documentation	0	8	August 6, 2025
Centerpoint exported scn.onnx which has input of 1*5, is it reasonable? cudnn	0	10	August 6, 2025
Caffe train super slow on RTX GPU cudnn , jetson	0	14	August 5, 2025
Struggling to get model onto tensorrt tensorrt , cuda , pytorch	3	693	August 5, 2025
Trtexec caffe model explicit batch	0	8	August 4, 2025
I bought the course "Deploying a Model on inference at scale" due to academic works I was not able to complete the labs with in the time @TomNVIDIA	1	18	August 4, 2025
Fan speed control and SW power cap RTX A5000	0	20	August 1, 2025
Memory problems arise when RTX50 series graphics cards are deployed at the same time cudnn , gaming	2	36	August 1, 2025
Using TensorRT models with NanoLLM causes memory leaks cudnn	0	16	August 1, 2025
The score output by the model, the result from torch, and the output from TensorRT 10.10 on x86 differ significantly? cudnn	0	11	August 1, 2025
Randomly getting `createInferRuntime: Error Code 6: API Usage Error (CUDA Initialization failure with error 3)` tensorrt , cuda , cudnn	2	110	July 31, 2025
/bin/bash: line 1: trtexec: command not found	1	18	July 31, 2025
Build yolov8 QAT model int8 engine failed cudnn	2	27	July 31, 2025
Cutlass cute-dsl error cuda , kernel	1	15	July 31, 2025
Impact CMake compile options on building serialized networks (trt)	1	16	July 31, 2025
INMSLayer: CUDA graph invalidation (DevicetoShapeHostCopy) cuda	2	29	July 31, 2025

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…