Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
- pyro
- jax
- hmc
- inference-algorithms
142,273 visible repositories in the index
2,233–2,256 of 10,969 · Most stars
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
Misago is fully featured modern forum application that is fast, scalable and responsive.
A command-line app for downloading Apple Music songs, albums, playlists, music videos, and uploaded videos.
PYthon svg GrAph plotting Library
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
Radically simplified static file serving for Python web apps
Apache Ossie, industry wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for semantic data
Motion planning algorithms commonly used on autonomous vehicles. (path planning + path tracking)
Interactive Redis: A Terminal Client for Redis with AutoCompletion and Syntax Highlighting.
Let Skills Evolve Collectively with Agentic Evolver
Unsupervised Learning for Image Registration
💰 Cryptocurrency Trading Bot for Binance (Experimental)
🎙️ A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
DeepWalk - Deep Learning for Graphs
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
Learning Chinese Character style with conditional GAN
基金投资管理回测引擎
An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)
Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama local stack.
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.