AI & Data Science Deep Learning (Training & Inference)

Riva NVIDIA Riva is a GPU-accelerated SDK for developing multimodal conversational AI applications that delivers real-time performance on GPUs. Triton Inference Server - archived Maxine Engage with NVIDIA directly and discuss the latest Maxine technology with a global developer community TensorRT 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.

Topic	Replies	Views	Activity
FastPitch retraining Riva cudnn , cublas , cufft	4	42	July 21, 2025
Performance Bottleneck on RTX 5080 with nvOCDR via Triton TensorRT cuda , deepstream	7	23	July 21, 2025
Licensing and Usage Terms for YOLO NAS Model TensorRT ai-training , ai	4	321	July 21, 2025
ROI Positioning Issue with nvdspreprocess and Mixed Resolutions Using New Streammux TensorRT deepstream	0	1	July 21, 2025
Memory problems arise when RTX50 series graphics cards are deployed at the same time TensorRT cudnn , gaming	0	1	July 21, 2025
TensorRT 10.8 on Windows: API Usage Error (Target GPU SM 120 is not supported by this TensorRT release.) TensorRT cudnn	4	605	July 20, 2025
Cutlass cute-dsl error TensorRT cuda , kernel	0	6	July 20, 2025
CUDA failed to initialize in Riva container on Windows + WSL 2 Riva cuda , gaming	2	13	July 20, 2025
Whisper deployment error on Nvidia T4 Riva	1	35	July 18, 2025
The shapes of output in .engine is 0, but the onnx works fine TensorRT	2	18	July 17, 2025
Randomly getting `createInferRuntime: Error Code 6: API Usage Error (CUDA Initialization failure with error 3)` TensorRT tensorrt , cuda , cudnn	0	12	July 16, 2025
Doesn't cudnn 9.10 support Conv1d operator in jetson platform? cuDNN cuda , pytorch , cudnn	0	13	July 16, 2025
Impact CMake compile options on building serialized networks (trt) TensorRT	0	8	July 15, 2025
Arm64 + gh200 LLM Engine issues TensorRT llama	0	13	July 15, 2025
Does TensorRT Model Optimizer Support aarch64 for LLaMA 3.1 Optimization? TensorRT tensorrt , llama	1	40	July 15, 2025
TensorRT Engine Outputs Identical Values for All Keypoints in ViT-based Model TensorRT deepstream	1	16	July 15, 2025
My account has been disabled TensorRT	3	61	July 14, 2025
It wont let me complete the "Augment your LLM Using Retrieval Augmented Generation" course TensorRT	5	212	July 14, 2025
New feature (AdaptivePool) TensorRT	0	8	July 14, 2025
cuDNN only selects sm80 kernels on blackwell devices cuDNN cudnn	0	12	July 13, 2025
Could you please help me extend the lab hours? TensorRT cudnn , ai-training	2	13	July 12, 2025
Bug: Q1 - the first Question in Generative AI Explained - no correct answers Maxine	21	2736	July 11, 2025
How to increase my lab hours for the digital learning course TensorRT	5	20	July 11, 2025
TensorRT produce all zero output for Qwen3-Embedding-0.6B TensorRT tensorrt , cuda , cudnn	5	111	July 11, 2025
About myelin_plugin.dll included in the TensorRT ZIP TensorRT	0	8	July 10, 2025
AI CONTEXT ENGINEERING TensorRT gaming	0	19	July 9, 2025
Megatron any-to-en conversion from nemo -> riva -> rmir Riva nemo	1	37	July 9, 2025
Strongly typed networks TensorRT 10.12 and above and best practices TensorRT tensorrt , onnx	0	25	July 9, 2025
Issues with Speaker Diarization in Riva ASR - when using model Whisper, Conformer-CTC Riva riva , generative_ai	1	31	July 9, 2025
About myelin_plugin.dll included in the TensorRT ZIP TensorRT	0	34	July 8, 2025