{"adoption": {"forks": 2046, "observed_at": "2026-08-28T04:10:41.569770+00:00", "stars": 10317}, "canonical_url": "https://ross.abutalabs.com/products/cutlass", "card": {"archived": false, "artifact_type": "library", "description": "CUDA Templates and Python DSLs for High-Performance Linear Algebra", "domain": ["deep-learning", "gpu-computing", "machine-learning", "performance"], "enriched": true, "function": ["machine-learning", "deep-learning", "gpu-computing", "math", "compiler"], "health_score": 100, "homepage": "https://docs.nvidia.com/cutlass/index.html", "language": "C++", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["NVIDIA/cutlass"], "name": "NVIDIA/cutlass", "platform": ["cpp", "python", "windows", "cross-platform"], "pushed_at": "2026-08-26T10:48:43+00:00", "repo": "NVIDIA/cutlass", "stars": 10317, "tags": ["cuda", "gemm", "linear-algebra", "tensor-cores", "kernels", "cute-dsl", "nvidia", "template-library", "algorithms", "gpu", "linux"], "topics": ["cuda", "deep-learning", "deep-learning-library", "cpp", "nvidia", "gpu", "python"], "urls": [], "use_cases": ["write custom high-performance GEMM kernels for NVIDIA GPUs", "prototype CUDA kernels in Python without deep C++ expertise", "implement mixed-precision matrix multiplication with FP16, BF16, FP8, or FP4 types", "integrate optimized tensor core kernels into deep learning frameworks", "tune tiling sizes and data movement strategies for GPU performance"], "what_it_is": "CUTLASS is NVIDIA's collection of CUDA C++ template abstractions and Python DSLs for implementing high-performance GEMM and related linear algebra computations on NVIDIA GPUs. It provides reusable, tunable kernel building blocks supporting many data types across Volta through Blackwell architectures.", "when_to_avoid": ["you just need a drop-in BLAS library rather than kernel building blocks (use cuBLAS)", "you target non-NVIDIA GPUs or CPUs", "you want a simple high-level API without performance tuning"], "when_to_choose": ["you need maximum GEMM or linear algebra performance on NVIDIA tensor cores", "you are developing custom CUDA kernels for deep learning or HPC", "you want a Python DSL for GPU kernel programming with C++-level performance", "you need support for the latest NVIDIA architectures and low-precision data types"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cutlass", "repo": "NVIDIA/cutlass", "role": "main", "score": 99}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:41.569770+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:19:10.942594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8828c718bc1363f1f6f41f4e089a2a23f311f960daf626aeac83a03e82f1d6be", "fetched_at": "2026-08-28T04:10:41.569770+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/cutlass"}, {"content_hash": "b74e75cd5c5cf8364ef74b4a7bc14e4e7d5b7dd1b1eeaae87c77faa32e8e43ad", "fetched_at": "2026-08-29T08:18:29.260212+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/cutlass/index.html"}, {"content_hash": "cc6bf3a690df64586885e6d73b0cf4ad534943e74e9344b261d212ea65a48c13", "fetched_at": "2026-08-29T08:18:29.269377+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/cutlass/latest"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 99}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3199, "days_push": 7, "days_rel": 7, "gap_med": 12, "n_releases_24m": 32}, "score": 99, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}