Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A high-throughput and memory-efficient inference and serving engine for LLMs

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

SGLang is a fast serving framework for large language models and vision language models.

Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

AICI: Prompts as (Wasm) Programs

RayLLM - LLMs on Ray

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

A throughput-oriented high-performance serving framework for LLMs

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

LLM (Large Language Model) FineTuning

Efficient AI Inference & Serving

A highly optimized LLM inference acceleration engine for Llama and its variants.

Multi-node production GenAI stack. Run the best of open source AI easily on your own servers. Easily add knowledge from documents and scrape websites. Create your own AI by fine-tuning open source models. Integrate LLMs with APIs. Run gptscript securely on the server

This is suite of the hands-on training materials that shows how to scale CV, NLP, time-series forecasting workloads with Ray.

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papers on accelerating LLMs, currently focusing mainly on inference acceleration, and related works will be gradually added in the future. Welcome contributions!