{"adoption": {"forks": 4492, "observed_at": "2026-08-28T04:11:35.325004+00:00", "stars": 23753}, "canonical_url": "https://ross.abutalabs.com/products/ncnn", "card": {"archived": false, "artifact_type": "library", "description": "ncnn is a high-performance neural network inference framework optimized for the mobile platform", "domain": ["deep-learning", "artificial-intelligence", "mobile-development", "embedded-systems", "cross-platform"], "enriched": true, "function": ["machine-learning", "llm-inference", "computer-vision", "image-processing", "gpu-computing"], "health_score": 99, "homepage": null, "language": "C++", "license": "NOASSERTION", "license_family": "other", "maturity": "stable", "member_repos": ["Tencent/ncnn"], "name": "Tencent/ncnn", "platform": ["cpp", "cross-platform", "wasm", "windows", "embedded"], "pushed_at": "2026-08-25T03:21:15+00:00", "repo": "Tencent/ncnn", "stars": 23753, "tags": ["neural-network-inference", "vulkan", "arm-neon", "simd", "model-conversion", "pnnx", "onnx", "pytorch", "edge-deployment", "mobile-ai", "android", "ios", "mobile", "desktop", "linux", "macos", "gpu"], "topics": ["inference", "high-preformance", "simd", "arm-neon", "deep-learning", "artificial-intelligence", "android", "ios", "ncnn", "vulkan", "neural-network", "caffe", "mxnet", "pytorch", "onnx", "darknet", "tensorflow", "mlir", "keras", "riscv"], "urls": [], "use_cases": ["run deep learning models on android and ios apps", "deploy neural network inference on edge devices without dependencies", "convert pytorch or onnx models to a mobile-friendly format", "accelerate inference with vulkan gpu on phones and pcs", "run computer vision models like object detection on mobile", "embed neural network inference in c++ applications"], "what_it_is": "ncnn is a high-performance neural network inference framework written in C++ and optimized for mobile, embedded, and desktop deployment. It has no third-party runtime dependencies, supports CPU and Vulkan GPU backends, and includes tools like pnnx for converting PyTorch and ONNX models.", "when_to_avoid": ["you need training or fine-tuning, not just inference", "you want a python-first workflow with rich ecosystem tooling", "you need large transformer/llm serving features out of the box", "you prefer a framework with extensive prebuilt model zoo and cloud integration"], "when_to_choose": ["you need fast on-device inference on mobile or embedded hardware", "you want a dependency-free c++ inference runtime", "you need cpu (arm neon) and vulkan gpu support", "you are deploying models in production mobile apps"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ncnn", "repo": "Tencent/ncnn", "role": "main", "score": 86}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.325004+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:56:21.245077+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3038d2dd648ec377e3891b640d843b5e33a4aa1f5c5c745f20707d42d47e7bba", "fetched_at": "2026-08-28T04:11:35.325004+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/ncnn"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 62}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3351, "days_push": 8, "days_rel": 99, "gap_med": 123, "n_releases_24m": 6}, "score": 86, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}