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	6147	January 10, 2025
Best practices for reporting an issue or bug relating to TensorRT	0	8980	September 21, 2018
Langserve error in Assessment - Building RAG agents with LLMs dli , llama3-8b-instruct , nv-embed-v1	0	2	January 23, 2026
Getting error "/usr/local/bin/nvidia_entrypoint.sh: line 33: exec: trtserver: not found"	3	4676	January 23, 2026
R&D inquiry: perceptual depth approach for 2D video on flat displays (pilot contact)	0	5	January 20, 2026
Nvfp4 Dynamic Quantizer Very Slow with Bias cudnn , tensorrt-model-optimizer	2	21	January 8, 2026
Optimising AI reasoning pipeline – Layer 2 + 3 merge for CPU efficiency cudnn	1	18	January 8, 2026
RAG app chat not working -> unexpected error	1	26	January 8, 2026
INT8 throughput and latency worse than FP16 for MiDas DPT Hybrid model on Thor tensorrt	3	57	January 6, 2026
cuDNN no longer included with CUDA Toolkit creates major friction for C++ ML toolchains cudnn , gaming	3	60	January 5, 2026
Forcing NHWC Layout for Convolutions in Mixed CNN-Transformer Graphs (TensorRT 10.10 - Blackwell) tensorrt , camera , cuda	2	33	January 4, 2026
Quantized GeMM using fp32 for Q/DQ layers cudnn , tensorrt-model-optimizer	0	20	January 2, 2026
Launch error when trying to to access to Fundamentals of deep learning	7	197	January 1, 2026
Fail to build nn.Conv2d in TensorRT-10 with large max_shape for DynamicShape tensorrt , pytorch	2	58	December 31, 2025
TensorRT: Quantization issues with convtranspose3D tensorrt , cuda , kernel , cudnn	3	33	December 31, 2025
NvRadarNet: Free space detection driveworks-radar	3	104	December 30, 2025
Severe FPS Drop (25 → 2–3 FPS) When Running YOLO in Docker Using L4T Base Image on NVIDIA Jetson	4	32	December 30, 2025
Jetson Orin Nano (JetPack 5.x): torchvision C++ ops (_C) fail to load with PyTorch 2.0.0+nv23.05 jetson	2	22	December 30, 2025
Worse performance after quantization on TensorRT cudnn , onnx , tensorrt-model-optimizer , jetson-orin	1	65	December 23, 2025
FinC2E — Governance-First AI for AML/KYC & Audit-Ready Decision Support (Human-in-the-Loop) architecture-and-design , system-management-and-architecture , aerial-research-cloud	1	26	December 22, 2025
How can I add custom parser to SGIE? cudnn	2	29	December 22, 2025
個人開発：ローカル完結型・学習する動画自動編集AIの設計について意見をいただきたい ai	3	51	December 18, 2025
RTX 5090 + Tensorrt + SDXL / Image Generation : Impossible ? Comfy-UI (Runpod) tensorrt , cudnn	4	166	December 16, 2025
Deterministic Inference at Scale: Moving Beyond Agents and MoE in Regulated Workloads jetson-inference , inference-server-triton , nim , llama	2	70	December 15, 2025
[TensorRT 10.x] Is ConvTranspose3d supported in INT8 on Jetson? (QAT Workflow) tensorrt , camera , cuda	4	69	December 9, 2025
Triton Inference Server not Loading yolo11 models	4	69	December 9, 2025
Onnx to engine failure of TensorRT 10.8.0 when running trtexec.exe on GPU 3060TI cudnn	2	64	December 8, 2025
TensorRT built-in NMS output lost when using Triton dynamic batching tensorrt , cudnn , inference-server-triton	3	99	December 16, 2025
TensorRT model export/inference tensorrt , tao	7	129	December 2, 2025
Issue with RTSP Camera Reconnection: Pipeline Breaks When Camera Comes Back Instantly camera , gstreamer , cudnn , deepstream	2	43	December 1, 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…