AI & Data Science Deep Learning (Training & Inference)

TensorRT Triton Inference Server (archived) cuDNN Riva NVIDIA Riva is a GPU-accelerated SDK for developing multimodal conversational AI applications that delivers real-time performance on GPUs. Frameworks (archived) Maxine Engage with NVIDIA directly and discuss the latest Maxine technology with a global developer community 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
TensorRT: Quantization issues with convtranspose3D TensorRT tensorrt , cuda , kernel , cudnn	1	1	December 13, 2025
Feature Request: ARM64 (Grace CPU) Support for Riva with Whisper Large-v3 Turbo Riva	0	1	December 13, 2025
RTX 5090 + Tensorrt + SDXL / Image Generation : Impossible ? Comfy-UI (Runpod) TensorRT tensorrt , cudnn	3	27	December 12, 2025
Problem with deploy fastconformer-rnnt asr model to nvidia-riva for streaming Riva	2	34	December 12, 2025
cudnnBackend api memory leak in calculate 1x1 convolution workspace size with ENGINEHEUR cuDNN cudnn	0	1	December 12, 2025
Deployment of finetuned Canary-1B model Riva	0	4	December 12, 2025
[TensorRT 10.x] Is ConvTranspose3d supported in INT8 on Jetson? (QAT Workflow) TensorRT tensorrt , camera , cuda	4	34	December 9, 2025
Forum Bot Test TensorRT cudnn	0	10	December 9, 2025
Triton Inference Server not Loading yolo11 models TensorRT	3	22	December 9, 2025
Onnx to engine failure of TensorRT 10.8.0 when running trtexec.exe on GPU 3060TI TensorRT cudnn	2	28	December 8, 2025
cuDNN no longer included with CUDA Toolkit creates major friction for C++ ML toolchains TensorRT cudnn , gaming	1	23	December 8, 2025
Riva faces difficulty in encoding a specific word Riva encoder , nemo , riva	1	549	December 3, 2025
Word boosting for the OOV word not working Riva riva , inception , nim	0	15	December 3, 2025
TensorRT built-in NMS output lost when using Triton dynamic batching TensorRT tensorrt , cudnn , inference-server-triton	2	56	December 2, 2025
TensorRT model export/inference TensorRT tensorrt , tao	6	89	December 2, 2025
Issue with RTSP Camera Reconnection: Pipeline Breaks When Camera Comes Back Instantly TensorRT camera , gstreamer , cudnn , deepstream	1	28	December 1, 2025
“Waiting for Riva server to load all Models” NVIDIA SPARK DGX Riva	5	82	December 1, 2025
CUDNN with GLIBC 2.42 cuDNN cuda , cudnn , jax	2	46	November 29, 2025
Does running isaacsim in DGX Spark support sensor data rendering TensorRT camera , kernel	2	33	November 28, 2025
Yolo-nas commercial use TensorRT yolo	2	35	November 28, 2025
"Error Code 3: API Usage Error (Parameter check failed, condition: isQuantized(dataType)." TensorRT jetson-inference , onnx , jetson	0	19	November 28, 2025
Compassion-Based Alignment Framework for Post-LLM AI Systems TensorRT	2	28	November 27, 2025
AI and CUDA Compatibility TensorRT cudnn	4	39	November 27, 2025
Jetson AGX Orin 64G: PyTorch RPC RuntimeError: CUDA IPC UUID Check Failure TensorRT cudnn	3	41	November 27, 2025
Improving AI Chatbot Accuracy with Fine-Tuned Models and Image Generation APIs TensorRT isaac-general	1	37	November 27, 2025
What is default optimization profile of an engine? TensorRT	3	39	November 27, 2025
TRT installation post TensorRT	2	21	November 26, 2025
Failing to load pruned model yolov7 using tensorrt model opt TensorRT tensorrt-model-optimizer	1	28	November 26, 2025
DeepStream 7.1: Using nvmsgconv msg2p-newapi=1 with full NvDsFrameMeta access — how to include NvDsAnalyticsFrameMeta in payload? TensorRT gstreamer , deepstream	1	48	November 26, 2025
"Error Code 10: Internal Error" when running trtexec for int8 TensorRT cudnn	6	434	November 25, 2025