{"adoption": {"forks": 388, "observed_at": "2026-08-28T04:08:57.559703+00:00", "stars": 4724}, "canonical_url": "https://ross.abutalabs.com/products/aitemplate", "card": {"archived": false, "artifact_type": "framework", "description": "AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.", "domain": ["deep-learning", "machine-learning", "gpu-computing", "performance"], "enriched": true, "function": ["deep-learning", "llm-inference", "compiler", "gpu-computing"], "health_score": 78, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["facebookincubator/AITemplate"], "name": "facebookincubator/AITemplate", "platform": ["python"], "pushed_at": "2026-08-07T07:10:39+00:00", "repo": "facebookincubator/AITemplate", "stars": 4724, "tags": ["cuda", "hip", "amd-gpu", "nvidia-gpu", "fp16", "tensorcore", "inference-serving", "code-generation", "kernel-fusion", "linux", "gpu"], "topics": [], "urls": [], "use_cases": ["serve fp16 transformer models like BERT or Stable Diffusion at near-roofline GPU performance", "compile neural networks into portable self-contained inference binaries", "run the same model efficiently on both NVIDIA and AMD GPUs", "fuse GEMM, LayerNorm, and elementwise ops into single GPU kernels", "deploy inference without PyTorch or CUDA runtime library dependencies", "add custom fused operators via simple Python codegen extensions"], "what_it_is": "AITemplate is a Python framework that compiles deep neural networks into high-performance CUDA (NVIDIA) or HIP (AMD) C++ code for fast fp16 inference. It generates self-contained binaries with advanced horizontal, vertical, and memory kernel fusions without depending on third-party libraries like cuDNN or TensorRT.", "when_to_avoid": ["you need training or gradient support - it is inference-only", "you need fp32/int8 quantization or CPU inference", "you want a mature, actively evolving ecosystem - consider alternatives like TensorRT or torch.compile", "your workflow depends on dynamic shapes beyond its supported range"], "when_to_choose": ["you need maximum fp16 inference throughput on NVIDIA or AMD GPUs", "you want self-contained binaries free of cuDNN/cuBLAS/TensorRT dependencies", "your models (ResNet, BERT, ViT, Stable Diffusion) benefit from aggressive kernel fusion", "you need one framework targeting both CUDA and HIP"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/aitemplate", "repo": "facebookincubator/AITemplate", "role": "main", "score": 66}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.559703+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:19:04.686408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "665f06a48a0404f86b5a9292b919ecb5beeaf08703171287ad5a69abcc35f712", "fetched_at": "2026-08-28T04:08:57.559703+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookincubator/AITemplate"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1510, "days_push": 26, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 66, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}