{"data":{"slug":"gpustack-gpustack","name":"gpustack","tagline":"A GPU cluster manager for high-performance AI model serving and on-demand SSH-accessible GPU instances","github_url":"https://github.com/gpustack/gpustack","owner":"gpustack","repo":"gpustack","owner_avatar_url":"https://avatars.githubusercontent.com/u/169020824?v=4","primary_language":"Python","stars":5710,"forks":650,"topics":["ascend","cuda","deepseek","distributed-inference","genai","high-performance-inference","inference","llama","llm","llm-inference","llm-serving","maas","mindie","openai","qwen","rocm","sglang","vllm"],"archived":false,"github_pushed_at":"2026-09-17T07:02:12+00:00","maintenance_label":"Very active","stars_delta_30d":256,"url":"https://www.graphcanon.com/tools/gpustack-gpustack","markdown_url":"https://www.graphcanon.com/tools/gpustack-gpustack.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/gpustack-gpustack","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=gpustack-gpustack","description":"A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.","homepage_url":"https://gpustack.ai","license":"Apache-2.0","open_issues":700,"watchers":45,"ai_summary":"gpustack/gpustack is a tool for managing GPU clusters, facilitating high-performance AI model serving and providing on-demand SSH-accessible GPU instances. It supports various AI frameworks and technologies, including vLLM, SGLang, and more.","readme_excerpt":"### Install GPUStack\n\nRun the following command to install and start the GPUStack server using Docker:\n\n```bash\nsudo docker run -d --name gpustack \\\n    --restart unless-stopped \\\n    -p 80:80 \\\n    --volume gpustack-data:/var/lib/gpustack \\\n    gpustack/gpustack\n```\n\n<details>\n<summary>Alternative: Use Quay Container Registry Mirror</summary>\n\nIf you cannot pull images from `Docker Hub` or the download is very slow, you can use our `Quay.io` mirror by pointing your registry to `quay.io`:\n\n```bash\nsudo docker run -d --name gpustack \\\n    --restart unless-stopped \\\n    -p 80:80 \\\n    --volume gpustack-data:/var/lib/gpustack \\\n    quay.io/gpustack/gpustack \\\n    --system-default-container-registry quay.io\n```\n</details>\n\nCheck the GPUStack startup logs:\n\n```bash\nsudo docker logs -f gpustack\n```\n\nAfter GPUStack starts, run the following command to get the default admin password:\n\n```bash\nsudo docker exec gpustack cat /var/lib/gpustack/initial_admin_password\n```\n\nOpen your browser and navigate to `http://your_host_ip` to access the GPUStack UI. Use the default username `admin` and the password you retrieved above to log in.\n\n---\n\n## License\n\nCopyright (c) 2024-2026 The GPUStack authors\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at [LICENSE](./LICENSE) file for details.\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License.","github_created_at":"2024-05-11T03:41:58+00:00","created_at":"2026-07-11T10:40:03.824313+00:00","updated_at":"2026-09-20T04:30:43.999334+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"ascend","name":"ascend"},{"slug":"cuda","name":"cuda"},{"slug":"deepseek","name":"deepseek"},{"slug":"distributed-inference","name":"distributed-inference"},{"slug":"genai","name":"genai"},{"slug":"high-performance-inference","name":"high-performance-inference"},{"slug":"inference","name":"inference"},{"slug":"llama","name":"llama"}],"trust":{"provenance":{"is_fork":false,"github_id":799049436,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:25:39.484Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":7,"days_since_push":1,"last_release_at":"2026-09-01T13:08:10Z","stars_delta_30d":256,"open_issues_delta_30d":27},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:25:41.128Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:25:38.404Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-18T08:25:38.404Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:25:38.404Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:25:38.404Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"gpustack is free to use under the Apache License, Version 2.0, but users may incur costs related to the infrastructure and resources used to run the tool."},"requirements":{"notes":["gpustack requires Docker for installation and management.","Ensure that the Docker environment is properly set up and that the user has the necessary permissions to run Docker commands."],"min_ram_gb":4,"requires_docker":true},"constraints":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":true},"when_to_use":["When you need to manage a GPU cluster for high-performance AI model serving and require on-demand SSH-accessible GPU instances.","If your project involves the use of specific AI frameworks and technologies such as vLLM and SGLang, which are supported by gpustack.","When you prefer a solution that can be easily installed and started using Docker, allowing for quick setup and management of GPU resources."],"when_not_to_use":["If your project does not require the specific AI frameworks and technologies supported by gpustack, such as vLLM and SGLang, and you need broader support.","When you are looking for a solution that does not rely on Docker for deployment, as gpustack requires Docker for installation and management.","If you need a tool that provides more extensive customization options beyond what gpustack offers, as it may not be as flexible in terms of configuration."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:56:59.311Z"},"constraint_facets":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":true},"decision_summary":[{"label":"Pricing","value":"freemium - gpustack is free to use under the Apache License, Version 2.0, but users may incur costs related to the infrastructure and resources used to run the tool."},{"label":"Requirements","value":"Min 4 GB RAM; Requires Docker; gpustack requires Docker for installation and management.; Ensure that the Docker environment is properly set up and that the user has the necessary permissions to run Docker commands."},{"label":"Adopt for","value":"gpustack is a GPU cluster manager that supports high-performance AI model serving and on-demand SSH-accessible GPU instances, suitable for environments requiring robust management of GPU resources and support for various"},{"label":"License detail","value":"gpustack is licensed under the Apache License, Version 2.0, which allows for free use, modification, and distribution of the software, provided that the license terms are adhered to."}]}}