{"adoption": {"forks": 1211, "observed_at": "2026-08-28T04:11:27.054928+00:00", "stars": 18739}, "canonical_url": "https://ross.abutalabs.com/products/ml-engineering", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Machine Learning Engineering Open Book", "domain": ["large-language-models", "machine-learning", "deep-learning", "gpu-computing", "tutorials", "developer-tools"], "enriched": true, "function": ["machine-learning", "llm-training", "llm-inference", "developer-tools", "documentation"], "health_score": 80, "homepage": "https://stasosphere.com/machine-learning/", "language": "Python", "license": "CC-BY-SA-4.0", "license_family": "other", "maturity": "active", "member_repos": ["stas00/ml-engineering"], "name": "stas00/ml-engineering", "platform": ["python", "cloud"], "pushed_at": "2026-08-26T00:27:36+00:00", "repo": "stas00/ml-engineering", "stars": 18739, "tags": ["open-book", "llm-training", "slurm", "pytorch", "distributed-training", "debugging", "gpu-clusters", "mlops", "fine-tuning", "multi-modal", "linux", "gpu"], "topics": ["pytorch", "slurm", "large-language-models", "llm", "machine-learning", "scalability", "transformers", "machine-learning-engineering", "mlops", "ai", "inference", "training", "debugging", "gpus", "network", "storage"], "urls": [], "use_cases": ["learn how to train large language models on multi-GPU clusters", "debug NCCL and distributed training failures", "decide when to upgrade GPUs for LLM training", "set up SLURM for machine learning workloads", "optimize storage and networking for LLM training", "fine-tune and run inference on LLMs and vision-language models", "troubleshoot OOM and performance bottlenecks in PyTorch training"], "what_it_is": "An open-source 'open book' of methodologies, scripts, and step-by-step instructions for training, fine-tuning, and running inference on large language and multi-modal models. It distills hands-on experience from projects like BLOOM-176B and IDEFICS-80B into practical guides covering hardware, networking, storage, SLURM orchestration, training, inference, and debugging.", "when_to_avoid": ["you are looking for a software library or tool to install and use directly", "you are a beginner seeking introductory ML tutorials", "you need formal, peer-reviewed textbook material rather than practitioner notes"], "when_to_choose": ["you are an ML engineer or operator training or fine-tuning LLMs/VLMs on GPU clusters", "you need practical, copy-paste commands and battle-tested debugging recipes", "you want to understand hardware, network, and storage choices for large-scale training"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ml-engineering", "repo": "stas00/ml-engineering", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:27.054928+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:01:19.101866+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3145c2661448e0c91ddd1cf6df221b2ba4e610060a841b2d32c47773c6c70702", "fetched_at": "2026-08-28T04:11:27.054928+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stas00/ml-engineering"}, {"content_hash": "ce844023c2930c6107ad35c6b1b1b15ed77b357343b7ed1aa21656c13c8957d5", "fetched_at": "2026-08-29T07:59:17.776712+00:00", "kind": "homepage", "missing": false, "url": "https://stasosphere.com/machine-learning/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2191, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}