{"adoption": {"forks": 672, "observed_at": "2026-08-28T04:09:25.802639+00:00", "stars": 5627}, "canonical_url": "https://ross.abutalabs.com/products/flash-linear-attention", "card": {"archived": false, "artifact_type": "library", "description": "🚀 Efficient implementations for emerging model architectures", "domain": ["large-language-models", "deep-learning", "machine-learning", "gpu-computing"], "enriched": true, "function": ["machine-learning", "llm-training", "llm-inference", "gpu-computing", "deep-learning"], "health_score": 100, "homepage": "https://github.com/fla-org/flash-linear-attention", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["fla-org/flash-linear-attention"], "name": "fla-org/flash-linear-attention", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T12:15:05+00:00", "repo": "fla-org/flash-linear-attention", "stars": 5627, "tags": ["linear-attention", "state-space-models", "triton-kernels", "sequence-modeling", "mamba", "gated-deltanet", "sparse-attention", "hybrid-architectures", "pytorch", "natural-language-processing", "gpu", "linux"], "topics": ["large-language-models", "machine-learning-systems", "natural-language-processing", "sequence-modeling"], "urls": [], "use_cases": ["implement linear attention layers for training LLMs", "run Mamba and state space model layers efficiently on GPU", "train hybrid attention and SSM language models", "use gated delta net kernels in my model", "benchmark efficient attention implementations across NVIDIA AMD and Intel GPUs", "build constant-memory sequence models for long context", "try emerging token mixing architectures like KDA and GDN-2"], "what_it_is": "A PyTorch library providing hardware-efficient implementations of emerging sequence model architectures, including linear attention, sparse attention, state space models (Mamba variants), and hybrid LLM layers. Kernels are written in Triton and related backends and verified on NVIDIA, AMD, and Intel GPUs.", "when_to_avoid": ["you only need standard softmax attention with no custom layers", "you work outside PyTorch or on CPU-only hardware", "you need a turnkey chatbot or inference server rather than model layers", "your project depends on fully stable, long-term-frozen APIs"], "when_to_choose": ["you need production-quality Triton kernels for linear attention or SSM layers", "you are training or fine-tuning LLMs with non-transformer or hybrid token mixing", "you want a single library covering many recent sequence-model papers", "you need multi-vendor GPU support (NVIDIA, AMD, Intel)"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/flash-linear-attention", "repo": "fla-org/flash-linear-attention", "role": "main", "score": 88}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:25.802639+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:55:21.398178+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90d21d467d3bd4a1d4cd4fdda19ba2d8d5c726971021a51a3d50ab0367375255", "fetched_at": "2026-08-28T04:09:25.802639+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "720ba67b2559a5763728c9e1d135fa6ab0f54fb36bbcb1a02c4e1f02c6beeca6", "fetched_at": "2026-08-29T08:49:57.721608+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/fla-org/flash-linear-attention"}, {"content_hash": "6745bc30119fe57a05d5bdff3741cde1158a5199ab99e04ca5fa75356ff44bac", "fetched_at": "2026-08-29T08:49:57.731032+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/flash-linear-attention/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 70, "rhythm": 83}, "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": 987, "days_push": 7, "days_rel": 37, "gap_med": 39.5, "n_releases_24m": 15}, "score": 88, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}