{"adoption": {"forks": 115, "observed_at": "2026-08-28T04:03:53.255338+00:00", "stars": 1179}, "canonical_url": "https://ross.abutalabs.com/products/flash-attention-minimal", "card": {"archived": false, "artifact_type": "library", "description": "Flash Attention in ~100 lines of CUDA (forward pass only)", "domain": ["deep-learning", "large-language-models", "gpu-computing", "developer-tools"], "enriched": true, "function": ["machine-learning", "deep-learning", "gpu-computing"], "health_score": 20, "homepage": null, "language": "Cuda", "license": "Apache-2.0", "license_family": "permissive", "maturity": "experimental", "member_repos": ["tspeterkim/flash-attention-minimal"], "name": "tspeterkim/flash-attention-minimal", "platform": ["python"], "pushed_at": "2024-12-30T04:17:28+00:00", "repo": "tspeterkim/flash-attention-minimal", "stars": 1179, "tags": ["flash-attention", "cuda-kernel", "educational", "pytorch-extension", "transformer-attention", "cuda", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["learn how flash attention works in CUDA", "understand shared memory tiling for attention", "benchmark flash attention vs manual attention", "study a minimal CUDA kernel for transformer attention", "starting point for writing custom attention kernels"], "what_it_is": "A minimal ~100-line CUDA re-implementation of the Flash Attention forward pass, loadable as a PyTorch extension. It is designed as an educational resource for CUDA beginners, following the notation of the original Flash Attention paper.", "when_to_avoid": ["you need a backward pass for training", "you need production performance or float16/tensor core support", "you need long sequence attention at scale", "you want a maintained, feature-complete attention library"], "when_to_choose": ["you want to learn how Flash Attention is implemented in CUDA", "you need a small readable reference implementation of the attention forward pass", "you are teaching or studying GPU kernel design for transformers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/flash-attention-minimal", "repo": "tspeterkim/flash-attention-minimal", "role": "main", "score": 25}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:53.255338+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:26:04.283681+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9abd545cbe2130f3a888cc21ee9020d0874dbdfdc08ef7b8d568a8db48be622d", "fetched_at": "2026-08-28T04:03:53.255338+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tspeterkim/flash-attention-minimal"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 64, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 909, "days_push": 611, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 25, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}