추론, 배포 및 런타임

ray

ray-project/ray

A distributed computing runtime for machine learning training, tuning and model serving.

★ 43.7K별점
⑂ 8K포크 수
3565미해결 이슈
Python언어
Apache-2.0라이선스
Q85편집 점수

개요

A distributed computing runtime for machine learning training, tuning and model serving. The repository is maintained under ray-project on GitHub. Its primary language is Python. See the [project README](https://github.com/ray-project/ray#readme) for the supported workflows.

주요 기능

  • A distributed computing runtime for machine learning training, tuning and model serving.

요구 사항, 설치 및 빠른 시작

Install Ray in a Python environment using the official installation guide. Select additional dependencies for the Ray libraries needed by your workload.

[Read the upstream installation and quickstart instructions](https://github.com/ray-project/ray#readme).

사용 정보

Start with the documented local example, confirm it runs with your resources, then connect it to your application using the supported interface.

[Usage examples and configuration reference](https://github.com/ray-project/ray#readme).

모델 호환성 및 사용 사례

저장소 메타데이터에 모델 호환성이 명시되어 있지 않습니다.

라이선스 및 위험 참고 사항

GitHub reports Apache-2.0 for this repository. Review the upstream license file; model weights, datasets and dependencies may have separate terms.

Source review 2026-09-05: GitHub search metadata and repository README. No runtime benchmark performed. License metadata: Apache-2.0.

릴리스 및 유지 관리

[View upstream releases](https://github.com/ray-project/ray/releases).

vllm

vllm-project/vllm

★ 89.5KPython

sglang

sgl-project/sglang

★ 32.2KPython

OpenVINO

openvinotoolkit/openvino

★ 10.6KC++

GPUStack

gpustack/gpustack

★ 5.4KPython