Starred repositories
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Tutorials for creating and using ONNX models
Cross-platform lib for process and system monitoring in Python
On-device AI across mobile, embedded and edge for PyTorch
A native PyTorch Library for large model training
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training
HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of HierarchicalKV is to store key-value feature-embeddings on h…
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
Service Discovery and Governance Platform for Microservice and Distributed Architecture
Fay is an open-source digital human framework integrating language models and digital characters. It offers retail, assistant, and agent versions for diverse applications like virtual shopping guid…
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
Open source codebase powering the HuggingChat app
MySQL Server, the world's most popular open source database, and MySQL Cluster, a real-time, open source transactional database.
OceanBase is an enterprise distributed relational database with high availability, high performance, horizontal scalability, and compatibility with SQL standards.
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
Apache NuttX is a mature, real-time embedded operating system (RTOS)
Embedded graphics library to create beautiful UIs for any MCU, MPU and display type.
Facebook's branch of Apache Thrift, including a new C++ server.
lightweight, standalone C++ inference engine for Google's Gemma models.