More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

Deploy DL/ ML inference pipelines with minimal extra code.

Set up CI in DL/ cuda/ cudnn/ TensorRT/ onnx2trt/ onnxruntime/ onnxsim/ Pytorch/ Triton-Inference-Server/ Bazel/ Tesseract/ PaddleOCR/ NVIDIA-docker/ minIO/ Supervisord on AGX or PC from scratch.

This repository serves as an example of deploying the YOLO models on Triton Server for performance and testing purposes

Provides an ensemble model to deploy a YoloV8 ONNX model to Triton

Proxy server for triton gRPC server that inferences embedding model in Rust

This repository utilizes the Triton Inference Server Client, which streamlines the complexity of model deployment.

The Purpose of this repository is to create a DeepStream/Triton-Server sample application that utilizes yolov7, yolov7-qat, yolov9 models to perform inference on video files or RTSP streams.

A template for delpoy AI server use django with tf_serving or triton_inference_serving

This repository provides an out-of-the-box deployment solution for creating an end-to-end procedure to train, deploy, and use Yolov7 models on Nvidia GPUs using Triton Server and Deepstream.

NvDsInferYolov7EfficientNMS for Gst-nvinferserver

Triton Inference Server Deployment with ONNX Models

This is a cutom triton-inference-server backend demo for process image (resize + norm)

Pipeline to insert text embeddings generated from self hosted embedding model into qdrant vector database using grpc in rust

QuickStart for Deploying a Basic Model on the Triton Inference Server

Add Some plus extra features to transformers