{"adoption": {"forks": 806, "observed_at": "2026-08-28T04:08:07.595112+00:00", "stars": 3504}, "canonical_url": "https://ross.abutalabs.com/products/transformerengine", "card": {"archived": false, "artifact_type": "library", "description": "A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.", "domain": ["deep-learning", "large-language-models", "machine-learning", "gpu-computing"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-training", "llm-inference", "gpu-computing", "transformers"], "health_score": 100, "homepage": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["NVIDIA/TransformerEngine"], "name": "NVIDIA/TransformerEngine", "platform": ["python"], "pushed_at": "2026-08-26T20:40:56+00:00", "repo": "NVIDIA/TransformerEngine", "stars": 3504, "tags": ["fp8", "fp4", "mixed-precision", "pytorch", "jax", "nvidia", "quantization", "transformer-models", "linux", "gpu", "cuda"], "topics": ["cuda", "deep-learning", "gpu", "machine-learning", "python", "pytorch", "fp8", "jax", "fp4"], "urls": [], "use_cases": ["train large language models in fp8 precision on nvidia gpus", "speed up transformer training with lower memory usage", "use nvfp4 mixed precision on blackwell gpus", "integrate fp8 support into a custom deep learning framework via c++ api", "train mixture-of-experts models with fused kernels", "run reinforcement learning training with end-to-end fp8 precision"], "what_it_is": "Transformer Engine is an NVIDIA library for accelerating Transformer model training and inference on NVIDIA GPUs using low-precision formats like FP8, MXFP8, and NVFP4. It provides optimized building blocks and an AMP-like API for PyTorch and JAX, plus a framework-agnostic C++ API.", "when_to_avoid": ["you train on non-NVIDIA GPUs or CPU-only hardware", "your models are small and don't benefit from low-precision GEMM speedups", "you need a framework-agnostic solution without CUDA dependencies"], "when_to_choose": ["you train or fine-tune large Transformer models on NVIDIA Hopper, Ada, or Blackwell GPUs", "you need FP8/FP4 low-precision training with minimal accuracy loss", "you use PyTorch or JAX and want drop-in accelerated Transformer layers", "you need MoE, tensor parallelism, and fused operations at scale"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/transformerengine", "repo": "NVIDIA/TransformerEngine", "role": "main", "score": 99}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.595112+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:35:46.693541+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aa556d531bf1c0af7b4361c18ba77c4dc494f843ee553a94d4505d1c099fed42", "fetched_at": "2026-08-28T04:08:07.595112+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TransformerEngine"}, {"content_hash": "e558870537364d82cecb1c0f2e68fa4a1d241b862c82934863d1bcf3a6ff99ea", "fetched_at": "2026-08-29T09:29:50.639501+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html"}, {"content_hash": "4fda13f1538dc348a062f5aabb9c16afeb5e5f74fa4be51bada8b4f81bb74e8d", "fetched_at": "2026-08-29T09:29:50.665812+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_blockwise_scaling/fp8_blockwise_scaling.html"}, {"content_hash": "2cc4cd93e7a5fc9a7a450a860ed3f37398991d2c4faaa2ea00101f906944e2ca", "fetched_at": "2026-08-29T09:29:50.648984+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/installation.html"}, {"content_hash": "6db783edf0b9c2d1175cc2b1bf482d155137c263c290d7a5a9a6ae3ec50be5fb", "fetched_at": "2026-08-29T09:29:50.651482+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/faq.html"}, {"content_hash": "5e9b428b6da235f420bea997e2bb9562ed3896cf112892a07be9f3ae32c8a1eb", "fetched_at": "2026-08-29T09:29:50.653649+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/index.html"}, {"content_hash": "b8b67c0dd282c697eb12221564aa2a9d59aa88dd6b1bffe97e6a02fc9fe52bd1", "fetched_at": "2026-08-29T09:29:50.655544+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/introduction/introduction.html"}, {"content_hash": "b75a4b9334f4a23840b8bedb5937fe01c2fd8e27c439fb7fd79f493ca72e76ab", "fetched_at": "2026-08-29T09:29:50.658168+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/performance_considerations/performance_considerations.html"}, {"content_hash": "4cfdeaee2a4777f4192180c55cbc7b649c19f1b345f8c65b25e350f12829f77a", "fetched_at": "2026-08-29T09:29:50.661133+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_current_scaling/fp8_current_scaling.html"}, {"content_hash": "d753f5fd558e87ebbffdfdc97b4e99c92be8b060321a1e126a400cea20174067", "fetched_at": "2026-08-29T09:29:50.663622+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/features/low_precision_training/fp8_delayed_scaling/fp8_delayed_scaling.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 98}, "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": 1443, "days_push": 7, "days_rel": 19, "gap_med": 26, "n_releases_24m": 26}, "score": 99, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}