{"adoption": {"forks": 102, "observed_at": "2026-08-28T04:03:18.542806+00:00", "stars": 1033}, "canonical_url": "https://ross.abutalabs.com/products/spargeattn", "card": {"archived": false, "artifact_type": "library", "description": "[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.", "domain": ["deep-learning", "large-language-models", "gpu-computing", "image-processing"], "enriched": true, "function": ["machine-learning", "llm-inference", "gpu-computing", "sdk"], "health_score": 61, "homepage": "https://arxiv.org/abs/2502.18137", "language": "Cuda", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["thu-ml/SpargeAttn"], "name": "thu-ml/SpargeAttn", "platform": ["python"], "pushed_at": "2026-02-25T00:07:21+00:00", "repo": "thu-ml/SpargeAttn", "stars": 1033, "tags": ["sparse-attention", "quantization", "inference-acceleration", "training-free", "video-generation", "vision-transformer", "sageattention", "cuda-kernel", "icml2025", "video", "gpu", "cuda"], "topics": ["ai-infra", "attention", "inference-acceleration", "llm", "mlsys", "quantization", "sparse-attention", "vision-transformer", "sageattention", "video-generation", "vit"], "urls": [], "use_cases": ["speed up LLM inference with sparse attention", "accelerate video generation model inference", "accelerate diffusion transformer image generation", "drop-in replacement for attention in PyTorch models", "apply custom block-sparse attention masks per head", "balance attention accuracy vs speed with topk sparsity"], "what_it_is": "SpargeAttn is the official implementation of a training-free sparse and quantized attention method that accelerates inference for language, image, and video models. It provides plug-and-play CUDA APIs (built on SageAttention2++) that skip matrix multiplications via a two-stage online filter while preserving end-to-end accuracy.", "when_to_avoid": ["you need CPU or non-CUDA hardware support", "you require exact dense attention outputs with no approximation", "your model uses very short sequences where sparsity gains are minimal"], "when_to_choose": ["you need faster attention inference on NVIDIA GPUs without retraining", "you run long-context LLMs or video/image generation models where attention dominates latency", "you want a plug-and-play sparse attention kernel compatible with SageAttention"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/spargeattn", "repo": "thu-ml/SpargeAttn", "role": "main", "score": 51}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:18.542806+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:06:41.987545+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f4e8c56e5b1cecdc0fa4fe4a3135732c87e505773b954059a21e6a79daeb023", "fetched_at": "2026-08-28T04:03:18.542806+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-ml/SpargeAttn"}, {"content_hash": "e0c8806e12ee17164b25f87bd159c107427a3b010640a738d30a878eb51a1caa", "fetched_at": "2026-08-29T13:06:22.219929+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2502.18137"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:06:22.229324+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:06:22.232831+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:06:22.234598+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:06:22.231134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 69, "longevity": 39, "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": 554, "days_push": 190, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 51, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}