LLM inference in C/C++

ClickHouse® is a real-time analytics DBMS

Port of OpenAI's Whisper model in C/C++

A library for efficient similarity search and clustering of dense vectors.

The Serenity Operating System 🐞

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Development repository for the Triton language and compiler

Tensor library for machine learning

Unsupervised text tokenizer for Neural Network-based text generation.

Enabling the Windows Subsystem for Linux to include support for Wayland and X server related scenarios

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

Transformer related optimization, including BERT, GPT

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

Patterns and behaviors for GPU computing

llm deploy project based mnn.

Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)