{"adoption": {"forks": 246, "observed_at": "2026-08-28T04:07:39.490990+00:00", "stars": 3045}, "canonical_url": "https://ross.abutalabs.com/products/distributed-llama", "card": {"archived": false, "artifact_type": "application", "description": "Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.", "domain": ["large-language-models", "microservices", "artificial-intelligence"], "enriched": true, "function": ["llm-inference", "cli", "rpc"], "health_score": 92, "homepage": null, "language": "C++", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["b4rtaz/distributed-llama"], "name": "b4rtaz/distributed-llama", "platform": ["windows", "cpp", "cli"], "pushed_at": "2026-07-05T16:47:20+00:00", "repo": "b4rtaz/distributed-llama", "stars": 3045, "tags": ["tensor-parallelism", "llama", "qwen", "vulkan", "raspberry-pi", "cluster-computing", "cpu-inference", "linux", "macos", "gpu"], "topics": ["distributed-computing", "llama2", "llm", "llm-inference", "neural-network", "llms", "open-llm", "distributed-llm", "llama3"], "urls": [], "use_cases": ["run llama 3 70b across multiple mac minis", "speed up llm inference by pooling home devices", "serve a large language model on raspberry pi cluster", "distributed inference of qwen 3 models", "run deepseek r1 distilled model locally on weak hardware", "tensor parallel llm inference over ethernet"], "what_it_is": "A C++ application that connects multiple home devices into a cluster for distributed LLM inference using tensor parallelism. It supports Llama, DeepSeek, and Qwen models on CPU (ARM and x86_64 AVX2) and experimentally on GPU via Vulkan.", "when_to_avoid": ["you have a single powerful GPU that fits the model", "you need production-grade serving with APIs and batching", "you need broad model format support beyond supported families"], "when_to_choose": ["you have several networked devices and want to run models too large for any single one", "you want CPU-only distributed inference without a GPU", "you want a simple single-command setup for popular open LLMs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/distributed-llama", "repo": "b4rtaz/distributed-llama", "role": "main", "score": 79}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:39.490990+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:28:57.578954+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cbd1fcc720e7c17845fa38141487cdbb89bb1b6e6983a7dd922493f31495080a", "fetched_at": "2026-08-28T04:07:39.490990+00:00", "kind": "readme", "missing": false, "url": "https://github.com/b4rtaz/distributed-llama"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 91, "longevity": 71, "rhythm": 68}, "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": 1003, "days_push": 59, "days_rel": 212, "gap_med": 4, "n_releases_24m": 40}, "score": 79, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}