{"adoption": {"forks": 265, "observed_at": "2026-08-28T04:07:21.998804+00:00", "stars": 2788}, "canonical_url": "https://ross.abutalabs.com/products/lucebox", "card": {"archived": false, "artifact_type": "service", "description": "LLM speculative inference server for heterogeneous hardware & consumer GPUs", "domain": ["large-language-models", "machine-learning", "gpu-computing", "self-hosted", "developer-tools"], "enriched": true, "function": ["llm-inference", "gpu-computing", "http-server", "sdk"], "health_score": 80, "homepage": "https://www.lucebox.com", "language": "C++", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["Luce-Org/lucebox"], "name": "Luce-Org/lucebox", "platform": ["self-hosted", "cpp"], "pushed_at": "2026-08-26T20:33:36+00:00", "repo": "Luce-Org/lucebox", "stars": 2788, "tags": ["speculative-decoding", "speculative-prefill", "cuda-kernels", "rocm", "heterogeneous-computing", "consumer-gpus", "local-ai", "openai-compatible-api", "llama-cpp", "moe-inference", "paged-attention", "long-context", "linux", "gpu", "cuda"], "topics": ["kernel", "llama-cpp", "local-ai", "qwen", "rtx3090", "megakernel", "cuda", "cuda-kernels", "dflash", "luce", "speculative-decoding", "pflash", "speculative-prefill", "poolside", "spark", "rocm", "strix-halo", "heterogeneous-computing", "r9700"], "urls": [], "use_cases": ["run large language models locally on consumer GPUs", "speed up long-context prefill on a single GPU", "serve LLMs with an OpenAI-compatible API on self-hosted hardware", "combine unified memory and dedicated GPU for large-model inference", "get faster token generation with speculative decoding", "run inference across mixed CPU/GPU heterogeneous machines", "keep AI inference fully private on owned hardware"], "what_it_is": "Lucebox is an open-source LLM inference engine written in C++ with custom CUDA/HIP kernels, focused on speculative decoding and speculative prefill for heterogeneous hardware and consumer GPUs. It ships as a server with OpenAI- and Anthropic-compatible APIs and is tuned per model and hardware target (e.g., RTX 3090, Strix Halo, AMD R9700).", "when_to_avoid": ["you need broad multi-vendor model support beyond the tuned model list", "you require multi-node distributed inference at datacenter scale", "you need a Python ecosystem for custom model experimentation", "you only need CPU-only inference without GPU acceleration", "you want a mature, widely-deployed engine like vLLM with extensive community tooling"], "when_to_choose": ["you want maximum tokens/sec on consumer GPUs like RTX 3090 or AMD R9700", "you need fast time-to-first-token on very long prompts (64K-256K tokens)", "you want to mix unified-memory APUs with discrete GPUs in one inference setup", "you prefer a C++/CUDA engine with no Python, PyTorch, or Triton in the inference loop", "you want a plug-and-play private local AI server with compatible APIs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/lucebox", "repo": "Luce-Org/lucebox", "role": "main", "score": 59}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.998804+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T08:15:30.915873+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0aa143a8e8645d43c626d2e752668dc177d33e7b0bcf5223b8e2867e01a60e9c", "fetched_at": "2026-08-28T04:07:21.998804+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Luce-Org/lucebox"}, {"content_hash": "23754db0139139d3c98e11b6910448f0a0f654c6cddfa0d649c4b4b4bbabf5b4", "fetched_at": "2026-08-29T09:55:09.523806+00:00", "kind": "homepage", "missing": false, "url": "https://www.lucebox.com"}, {"content_hash": "ff894ee9f9233da5ca8248476ea71478c81ffce1f420bc8de49382b4b470ec6d", "fetched_at": "2026-08-29T09:55:09.529649+00:00", "kind": "site_page", "missing": false, "url": "https://www.lucebox.com/blog/pflash"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 10, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 152, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 59, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}