Starred repositories
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
The FreeBSD src tree publish-only repository. Experimenting with 'simple' pull requests....
Ongoing research training transformer models at scale
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Development repository for the Triton language and compiler
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
An Open Source Machine Learning Framework for Everyone
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
Open standard for machine learning interoperability
FlashInfer: Kernel Library for LLM Serving
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
Fast and memory-efficient exact attention
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON for ARM.
Visualizer for neural network, deep learning and machine learning models
Eclipse Theia is a cloud & desktop IDE framework implemented in TypeScript.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Scripts to build a wheel and a Docker image containing a complete ML framework stack, including dependencies, for AArch64 CPUs, as well as a selection of examples and benchmarks.
Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.
RT-Thread is an open source IoT Real-Time Operating System (RTOS). https://rt-thread.github.io/rt-thread/
This project focuses on enhancing construction site safety through real-time detection of safety gear such as helmets and vests worn by workers, as well as detecting the presence of a person.