ray is an open-source LLM inference tool from ray-project, licensed under Apache-2.0. It has 44k GitHub stars and 8.2k forks, and was last updated in October 2026. Docs and downloads are linked from ray.io.
“Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.”
— ray-project, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 44,063 |
| Forks | 8,171 |
| Language | Python |
| License | Apache-2.0 |
| Last updated | |
| Owner | ray-project |
| Website | ray.io |
| Repository | ray-project/ray |
Tags
data-sciencedeep-learningdeploymentdistributedhyperparameter-optimizationhyperparameter-searchlarge-language-modelsllm
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.