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	6216	January 10, 2025
Best practices for reporting an issue or bug relating to TensorRT	0	9008	September 21, 2018
ONNX model with less nodes or simplified runs slower	0	9	May 13, 2026
Tensorflow Container for use on H200? cudnn	0	8	May 13, 2026
Compression-aware AI training for AV pipelines us	0	15	May 12, 2026
Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) nim , agentic-ai , deepseek	0	7	May 12, 2026
TRT 10.14: dynamic-shape InstanceNormalization crashes with CUDA 720 in __myl_Inor kernel cudnn , deepstream	4	41	May 11, 2026
Request to enable "Public API Endpoints" permission for my personal organization ai-training , chinese , nim	2	49	May 8, 2026
Strange changes in file size when deployed with tensorrt tensorrt	8	935	May 7, 2026
Windows 11 + WSL2 Docker Desktop + RTX 5060 Ti 16GB: System GUI severe lag after idle hours with AI inference running (nvlddmkm.sys high DPC latency) cuda , kernel , ubuntu , gaming	2	65	May 5, 2026
Fail to Build the TRT Engine of a multi-GatherND ONNX Model for large input volume tensorrt , cudnn , onnx	0	26	May 1, 2026
Missing Public API Endpoints permission in Personal Organization – 403 Forbidden on integrate.api.nvidia.com	1	82	April 30, 2026
Deploying spconv-based 3D detection model (PillarNet) with TensorRT on aarch64 GB10 — libspconv SM120 missing	5	157	April 30, 2026
Error Code: 9: Skipping tactic 0x001526e231ae2e51 due to exception Cask convolution execution tensorrt	3	357	April 30, 2026
[CUDA][WSL2][MPS] CUDA OOM with >14 MPI ranks under WSL2; MPS not starting cuda	2	162	April 30, 2026
Issues with Using TensorRT on Jetson Orin Nano tensorrt , jetson	4	125	April 30, 2026
Model outputting NaNs tensorrt , cudnn , onnx	3	190	April 20, 2026
Custom layer fails when loading from engine file cudnn	4	65	April 14, 2026
Open-Source CLI Agent Framework for NVIDIA AI Endpoints - Seeking Feedback cudnn , ai , open-source-software , api , jetson , nim , llama , agentic-ai , deepseek , nemotron	7	258	April 23, 2026
EfficientDet training with customdata and resulting 0 mAP in evaluation:	11	299	April 3, 2026
Pthread_rwlock_rdlock is taking very long during TRT ExecutionContext::enqueue nsight	4	59	April 16, 2026
[NVIDIA Sizing LLM Inference Systems] Request for additional lab hours cudnn , ai-training	2	49	April 2, 2026
Question about data-dependent shapes in TensorRT	2	50	April 1, 2026
Custom YoloV8 model export to ONNX failed for DeepStream 9.0 deepstream	5	153	March 31, 2026
Issue: "Phone number has exceeded limits" error during first verification attempt ai , api , nim	2	138	March 31, 2026
[Bug?] Builder Internal Error Code 2 on RTX 6000 Ada (sm89) but succeeds on Blackwell (sm120) with IPluginV2DynamicExt + OBEY_PRECISION_CONSTRAINTS tensorrt , cudnn	2	51	March 31, 2026
TensorRT 10.7.0 on Orin Nano: Target GPU SM 87 is not supported by this TensorRT release tensorrt , cudnn , onnx , jetson , jetson-nano , jetson-orin	2	77	March 31, 2026
Getting phone number exceeds limits for build.nvidia verification api	1	46	March 30, 2026
TensorRT export fails on both Jetson AGX Orin and Thor but passes on RTX cudnn , jetson	4	121	March 25, 2026
Multiple CUDA streams for one tensorrt Model	3	68	April 2, 2026

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…