Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Quickly bring up your PyTorch project(a skeleton)

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activelo…

Visualizer for neural network, deep learning and machine learning models

A Lightweight, Cloud-Native Stateful Distributed Dataflow Engine

TextBox 2.0 is a text generation library with pre-trained language models

Solve puzzles. Improve your pytorch.

Foundation Architecture for (M)LLMs

Next generation of automated data exploratory analysis and visualization platform.

🦜🔗 Build context-aware reasoning applications

Tensor library for machine learning

The easiest way to serve AI apps and models - Build reliable Inference APIs, LLM apps, Multi-model chains, RAG service, and much more!

Implementation of popular deep learning networks with TensorRT network definition API

A GPipe implementation in PyTorch

Serving Inside Pytorch

lightweight, standalone C++ inference engine for Google's Gemma models.

Matrix and Parameter server. On GPU and CPU.

LLM training in simple, raw C/CUDA

System for AI Education Resource.

FlashInfer: Kernel Library for LLM Serving

《Machine Learning Systems: Design and Implementation》- Chinese Version

CUDA/Metal accelerated language model inference

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.