ray

Thresher - THRESHold EvaluatoR for Python / Spark / Ray

Scalable MLOps framework for distributed training and model deployment with PyTorch, Kubernetes, and Ray.

Disaggregated speculative decoding with Ray. Parallel draft workers + target verifier. 4.51x speedup, 52% acceptance rate, 1.5x throughput on GPT-2.

Benchmarking sequential vs. Ray-distributed RAG ingestion — MapReduce only beats single-process past ~15 MB. LangChain + FAISS + Ollama.

Ray distributed computing integration for RxPY

Python wrapper for starting distributed Ray clusters with LSF job submission

Debug Drupal applications using Ray

基于python分布式框架搭建Windows集群环境

A demo pipeline of using Redis as an online feature store with Feast for orchestration and Ray for training and model serving

A collection of Mathematica notebooks for some application areas.

This project focuses on distributed model training using Ray.io. It includes setup scripts, model training, evaluation tools, and Docker deployment, designed for efficient parallel processing and performance monitoring in machine learning workflows.

Rust client library for the Ray debugging app.

A scalable Kubernetes training factory for medical-image segmentation models.

Runnable Ray examples for learning distributed Python, from basics to Ray Data, Serve, Train, and Tune.

adrevo is an experimental system for agentic, AI-directed evolution of algorithms

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

Calculating the ground state energy of different molecules serially and parallel

A foundation for ray tracing using CUDA and parallel computing techniques.

Distributed ML inference across a desktop RTX 3060 and a Raspberry Pi 4B, connected with Ray.

基于 Isaac Lab + Ray 的分布式机器人策略评测平台。支持多 GPU 并行评测、Elo 排行榜、外部模型接入。FastAPI + React。