#real-time-inference Repositories
Discover 43 active open source GitHub repositories tagged with #real-time-inference, accumulating 133,583 total stars (averaging 3,106 stars per project). Leading this topic is facebookresearch/sam2 with 20,204 stars.
43 repositories total
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
An ultra-lightweight, real-time runnable digital human model on mobile devices
โ ๏ธDirectML is in maintenance mode โ ๏ธ DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm.
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
A TensorFlow implementation of this Nvidia paper: https://arxiv.org/pdf/1604.07316.pdf with some changes
A Self-adaptation Framework๐ that adapts LLMs for unseen tasks in real-time!
Bring portraits to life in Real Time๏ผonnx/tensorrt support๏ผReal-Time Portrait Driver๏ผ
Cross-Platform Production-ready C++ inference engine for YOLO models (v5-v12, YOLO26). Unified API for detection, segmentation, pose estimation, OBB, and classification. Built on ONNX Runtime and OpenCV. Optimized for CPU/GPU with quantization support.
RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything
The training program for libfacedetection for face detection and 5-landmark detection.
VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)
A simple demo of yolov5s running on rk3588/3588s using c++ (about 142 frames). / A simple demo of yolov5s running on rk3588/3588s using c++ (about 142 frames).
Notebooks and examples on how to onboard and use various features of Amazon Personalize
An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch
Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).
Ultralytics YOLO iOS app and Swift package for real-time Core ML inference across major computer vision tasks.
Official Ultralytics YOLO Flutter plugin for real-time inference on Android and iOS across major vision tasks.
Frequently Asked Questions
What is the most popular #real-time-inference repository on GitHub?
The top ranked open source #real-time-inference project on GitHub is facebookresearch/sam2 with 20,204 stars. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Which programming languages are most used in #real-time-inference repositories?
Among the top ranked #real-time-inference projects on GitHub, the most common programming languages are Python, Jupyter Notebook, C++, TypeScript.
How is the #real-time-inference repository ranking calculated?
We track 43 active open source repositories tagged with #real-time-inference (500+ stars), totaling 133,583 stars with an average of 3,106 stars per repository. Rankings update daily from the GitHub API.