An image to text model/pipeline using VIT and Transformers and deployment using Nvidia's Pytrition and Streamlit app.
-
Updated
May 2, 2023 - Python
An image to text model/pipeline using VIT and Transformers and deployment using Nvidia's Pytrition and Streamlit app.
Search Engine on Shopee apply Image Search, Full-text Search, Auto-complete
Streamlit Dockerized Computer Vision App with Triton Inference Server and PostgreSQL database
Serving YOLOv5 Segmentation Model with Amazon EC2 Inf1
Custom Yolov8x-cls edge model deployment and training to classify trash vs recycling.
Notebook with commands to convert a Detectron2 MaskRCNN model to TensorRT
Go gRPC client for YOLO-NAS, YOLOv8 inference using the Triton Inference Server.
Triton inference server with Python backend and transformers
The Sumen model integrates with Triton Inference Server
This repository is a code sample to serve Large Language Models (LLM) on a Google Kubernetes Engine (GKE) cluster with GPUs running NVIDIA Triton Inference Server with FasterTransformer backend.
Serving Example of CodeGen-350M-Mono-GPTJ on Triton Inference Server with Docker and Kubernetes
Example string processing pipeline on Triton Inference Server
Miscellaneous codes and writings for MLOps
Run Multiple Models on the Same GPU with Amazon SageMaker Multi-Model Endpoints Powered by NVIDIA Triton Inference Server. A Java client is also provided.
Microservices with HTTP, Triton Inference Server, FastApi and Docker-compose
An image retrieval system that utilizes deep learning ResNet for feature extraction, Local Optimized Product Quantization techniques for storage and retrieval, and efficient deployment using Nvidia technologies like TensorRT and Triton Server, all accessible through a FastAPI-powered web API.
TensorRT를 통한 Stable Diffusion 가속하기
Deploy KoGPT with Triton Inference Server
Add a description, image, and links to the triton-inference-server topic page so that developers can more easily learn about it.
To associate your repository with the triton-inference-server topic, visit your repo's landing page and select "manage topics."