Machine Learning · GitHub

This project applies machine learning techniques in Python to analyze data, visualize feature relationships, and perform classification using models such as Decision Tree and Support Vector Machine. Model performance is evaluated through confusion matrices and graphical analysis.

Pretrain and fine-tune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Deep learning introduction tutorial, excellent articles, Deep Learning Tutorial

Official PyTorch implementation of One-Minute Video Generation with Test-Time Training

SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

• Generate and edit: Create images or videos from text or images; edit, inpaint, outpaint, refine, detail
• Guide generation: Use LoRA, ControlNet, IP-Adapters, and Prompt enhancement

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A human-centric, resource-aware Android node for edge computing and federated learning. Orchestrates distributed intelligence with privacy-first localization and empathetic hardware management.

The central nervous system and backend orchestrator for Fractal. It handles multi-tenant task scheduling, real-time TFLOPs budgeting, and federated weight aggregation using FedAvg.

• Edge AI & Mobile Compute Orchestration Spotlight: Architectural overview and visual demonstration spotlighting on-device edge intelligence, distributed training rounds, and decentralized compute harvesting across mobile devices.

Making large AI models cheaper, faster and more accessible

• Data Parallelism
• Pipeline Parallelism

High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.

• Rocket Builder - Drag, connect, and configure nodes visually, no boilerplate. Real-time observability tracks token usage, LLM calls, latency, and execution. Pipelines are portable JSON, version-controllable, shareable, and runnable anywhere.
• High-Performance C++ Runtime - Native multithreading purpose-built for the throughput demands of AI and data workloads. No bottlenecks, no compromises for production scale.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

A unified ecosystem and workspace for large-scale federated learning of Large Models & LLMS. Store compute as Wifi

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠