{"adoption": {"forks": 595, "observed_at": "2026-08-28T04:10:37.054880+00:00", "stars": 9752}, "canonical_url": "https://ross.abutalabs.com/products/powerinfer", "card": {"archived": false, "artifact_type": "library", "description": "High-speed Large Language Model Serving for Local Deployment", "domain": ["large-language-models", "machine-learning", "gpu-computing"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning"], "health_score": 69, "homepage": null, "language": "C++", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["Tiiny-AI/PowerInfer"], "name": "Tiiny-AI/PowerInfer", "platform": ["windows", "cpp"], "pushed_at": "2026-05-11T06:48:06+00:00", "repo": "Tiiny-AI/PowerInfer", "stars": 9752, "tags": ["cpu-gpu-hybrid", "activation-locality", "sparse-models", "local-deployment", "consumer-gpu", "on-device-inference", "linux", "macos", "gpu", "android"], "topics": ["large-language-models", "llama", "llm", "llm-inference", "local-inference"], "urls": [], "use_cases": ["run an LLM locally on a consumer GPU", "serve large language models on a single desktop machine", "speed up inference of sparse ReLU-activated LLMs", "run LLM inference on a smartphone", "deploy Llama-style models offline on my own hardware"], "what_it_is": "PowerInfer is a CPU/GPU hybrid LLM inference engine that exploits activation locality to run large language models fast on consumer-grade hardware, including desktops and smartphones. It supports sparse models like TurboSparse and ProSparse and is MIT-licensed C++ software.", "when_to_avoid": ["you need multi-node distributed serving at datacenter scale", "you want a managed cloud inference API", "your models are not compatible with its supported architectures"], "when_to_choose": ["you want fast local LLM inference on consumer-grade CPU/GPU hardware", "you are using sparsified models like TurboSparse or ProSparse", "you need on-device inference on smartphones or edge devices"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/powerinfer", "repo": "Tiiny-AI/PowerInfer", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:37.054880+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:21:12.047785+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab468dfeb814bc4d34f4cb4c9dcfe4512a5b927d39f1d0bee33f845b1c20d146", "fetched_at": "2026-08-28T04:10:37.054880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tiiny-AI/PowerInfer"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 81, "longevity": 70, "rhythm": 35}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 993, "days_push": 114, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}