{"adoption": {"forks": 204, "observed_at": "2026-08-28T04:05:01.672836+00:00", "stars": 1547}, "canonical_url": "https://ross.abutalabs.com/products/streaming", "card": {"archived": false, "artifact_type": "library", "description": "A Data Streaming Library for Efficient Neural Network Training", "domain": ["deep-learning", "machine-learning", "cloud-computing"], "enriched": true, "function": ["streaming", "etl", "machine-learning", "data-science"], "health_score": 88, "homepage": "https://streaming.docs.mosaicml.com", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["mosaicml/streaming"], "name": "mosaicml/streaming", "platform": ["python", "cloud", "cross-platform"], "pushed_at": "2026-06-25T15:02:27+00:00", "repo": "mosaicml/streaming", "stars": 1547, "tags": ["pytorch", "streaming-dataset", "distributed-training", "cloud-storage", "mosaicml", "mds-format", "data-loader", "data-engineering", "docker"], "topics": ["dataset", "deep-learning", "machine-learning", "neural-network", "pytorch", "streaming"], "urls": [], "use_cases": ["stream training data from s3 to pytorch", "train large models on datasets stored in cloud storage", "distributed multi-node data loading for deep learning", "convert datasets to mds format for streaming", "resume training quickly without re-downloading data", "shuffle large datasets deterministically during training", "load huggingface datasets as streaming shards"], "what_it_is": "StreamingDataset is a Python library from MosaicML for fast, accurate streaming of training data from cloud object storage (S3, GCS, Azure, OCI, Databricks, HuggingFace) into PyTorch training jobs. It is designed for multi-node distributed training of large models, with deterministic shuffling, elastic resumption, and correctness guarantees.", "when_to_avoid": ["you only train on small local datasets where a plain DataLoader suffices", "you need a non-PyTorch framework integration", "you require interactive random access rather than sequential streaming"], "when_to_choose": ["you train deep learning models on large datasets in cloud object storage", "you need efficient multi-node distributed data loading with determinism", "you want fast, cheap streaming instead of downloading full datasets", "you use PyTorch and want a drop-in StreamingDataLoader"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/streaming", "repo": "mosaicml/streaming", "role": "main", "score": 70}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.672836+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:29.831317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a451a0e3ae388137fb45d60a2917a600dbf6a727dd70eea29beea0794eff4f8", "fetched_at": "2026-08-28T04:05:01.672836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mosaicml/streaming"}, {"content_hash": "46a9561d4b15236ba645829910ce7d4b1396a136eee32348b0b061fb016b300d", "fetched_at": "2026-08-29T11:31:35.825562+00:00", "kind": "homepage", "missing": false, "url": "https://streaming.docs.mosaicml.com"}, {"content_hash": "66f118758e1246b2fe2b275c5544bb9334f57516737eb961c7e0246cd2d65954", "fetched_at": "2026-08-29T11:31:35.834740+00:00", "kind": "site_page", "missing": false, "url": "https://docs.mosaicml.com/projects/streaming/en/stable/getting_started/faqs_and_tips.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 89, "longevity": 100, "rhythm": 28}, "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": 1546, "days_push": 69, "days_rel": 414, "gap_med": 42, "n_releases_24m": 6}, "score": 70, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}