{"adoption": {"forks": 628, "observed_at": "2026-08-28T04:09:22.365071+00:00", "stars": 5560}, "canonical_url": "https://ross.abutalabs.com/products/gpustack", "card": {"archived": false, "artifact_type": "service", "description": "A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.", "domain": ["large-language-models", "gpu-computing", "infrastructure-as-code", "cloud-computing", "self-hosted", "artificial-intelligence", "microservices"], "enriched": true, "function": ["llm-inference", "gpu-computing", "container-orchestration", "monitoring", "auth", "rate-limiting", "scheduling", "ssh", "api-gateway", "self-hosted"], "health_score": 100, "homepage": "https://gpustack.ai", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["gpustack/gpustack"], "name": "gpustack/gpustack", "platform": ["python", "self-hosted", "cloud"], "pushed_at": "2026-08-26T02:09:56+00:00", "repo": "gpustack/gpustack", "stars": 5560, "tags": ["gpu-cluster-manager", "model-as-a-service", "vllm", "sglang", "tensorrt-llm", "heterogeneous-gpu", "distributed-inference", "gpu-instances", "openai-compatible-api", "nvidia", "amd", "ascend", "rocm", "cuda", "speculative-decoding", "kv-cache", "multi-cluster", "metering", "rbac", "devops", "linux", "docker", "kubernetes"], "topics": ["ascend", "cuda", "deepseek", "distributed-inference", "genai", "inference", "llama", "llm", "maas", "openai", "qwen", "rocm", "vllm", "mindie", "llm-inference", "llm-serving", "sglang", "high-performance-inference"], "urls": [], "use_cases": ["manage a gpu cluster for llm inference", "serve openai-compatible llm apis on my own gpus", "deploy vllm or sglang across multiple gpu servers", "run large models with distributed inference on heterogeneous gpus", "provision ssh-accessible gpu instances for fine-tuning", "build a model-as-a-service platform for my team", "schedule llm workloads across nvidia and amd gpus", "monitor gpu utilization and token usage for model serving"], "what_it_is": "GPUStack is an open-source GPU cluster manager for AI model serving that orchestrates inference engines like vLLM, SGLang, and TensorRT-LLM across heterogeneous GPU hardware (NVIDIA, AMD, Ascend, and more) on-premises, in Kubernetes, or in the cloud. It also provisions on-demand SSH-accessible GPU instances and provides enterprise features such as monitoring, authentication, load balancing, and token metering for delivering Model-as-a-Service.", "when_to_avoid": ["you only need to run a single model on one local machine - simpler tools like Ollama or llama.cpp suffice", "your infrastructure is already standardized on Kubernetes and you prefer a native Kubernetes operator or KServe", "you need training or fine-tuning orchestration as the primary workload rather than inference serving", "you require Windows or macOS worker nodes - GPU workers are Linux-only"], "when_to_choose": ["you need to serve LLMs across a fleet of heterogeneous GPUs (NVIDIA, AMD, Ascend, etc.) with automatic engine selection", "you want an OpenAI-compatible API gateway with auth, rate limiting, and metering out of the box", "you need multi-cluster GPU management spanning on-premises servers, Kubernetes, and cloud providers", "you want day-0 support for newly released models via pluggable inference engines", "you need SSH-accessible GPU instances for development and fine-tuning workloads"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gpustack", "repo": "gpustack/gpustack", "role": "main", "score": 90}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.365071+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:55:38.199714+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "393c4d308f87cee8e31418e35c2906dca0a57598fe41a4e5ca20c9875cebe6ab", "fetched_at": "2026-08-28T04:09:22.365071+00:00", "kind": "readme", "missing": false, "url": "https://github.com/gpustack/gpustack"}, {"content_hash": "e86ac456e4656faebd23b9b80b2776bfaddd5cb5e120431b444d7f001a7eed88", "fetched_at": "2026-08-29T08:50:56.021693+00:00", "kind": "homepage", "missing": false, "url": "https://gpustack.ai"}, {"content_hash": "fedeae8b98b8d79ca0fad46b499f9c90064ab351a2bb3b54414bdbda44bed082", "fetched_at": "2026-08-29T08:50:56.033417+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/latest/quickstart"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T08:50:56.031578+00:00", "kind": "site_page", "missing": false, "url": "https://docs.gpustack.ai/"}, {"content_hash": "03370540b851f0047e45c3274756a19c86e557ff4557eaa071e56602b3af3c3d", "fetched_at": "2026-08-29T08:50:56.035210+00:00", "kind": "site_page", "missing": false, "url": "https://gpustack.ai/enterprise"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 60, "rhythm": 95}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 844, "days_push": 8, "days_rel": 33, "gap_med": 23.0, "n_releases_24m": 25}, "score": 90, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}