Official inference framework for 1-bit LLMs

A native PyTorch Library for large model training

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

You like pytorch? You like micrograd? You love tinygrad! ❤️

You can get a lifetime of FREE VPS using GitHub Codespaces with Kali Linux Docker image installed on github workspace terminal.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Scalable and user friendly neural 🧠 forecasting algorithms.

WangchanX Fine-tuning Pipeline

A simple, performant and scalable Jax LLM!

AutoMQ is a cloud-first alternative to Kafka by decoupling durability to S3 and EBS. 10x Cost-Effective. No Cross-AZ Traffic Cost. Autoscale in seconds. Single-digit ms latency.

AIOS: AI Agent Operating System

Go library for Google Firestore (Firebase).

An innovative library for efficient LLM inference via low-bit quantization

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Unified Training of Universal Time Series Forecasting Transformers

Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Large Action Model framework to develop AI Web Agents

High-performance key-value store for ML inference. 100x faster than Redis.

A graphics engine that executes entirely on the CPU

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Visualize the intermediate output of Mistral 7B

A set of modern Grafana dashboards for Kubernetes.

workshop materials to build intelligent solutions on Open AI