{"adoption": {"forks": 208, "observed_at": "2026-08-28T04:05:01.869682+00:00", "stars": 1548}, "canonical_url": "https://ross.abutalabs.com/products/turbotransformers", "card": {"archived": false, "artifact_type": "library", "description": "a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.", "domain": ["machine-learning", "deep-learning", "large-language-models"], "enriched": true, "function": ["llm-inference", "machine-learning", "nlp", "sdk"], "health_score": 39, "homepage": null, "language": "C++", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["Tencent/TurboTransformers"], "name": "Tencent/TurboTransformers", "platform": ["cpp", "python", "cross-platform"], "pushed_at": "2025-07-18T03:51:18+00:00", "repo": "Tencent/TurboTransformers", "stars": 1548, "tags": ["transformer-inference", "bert", "gpt2", "huggingface", "pytorch-plugin", "cpu-gpu", "smart-batching", "natural-language-processing", "linux", "gpu"], "topics": ["nlp", "transformer", "bert", "decoder", "gpu", "machine-translation", "inference", "huggingface-transformers", "pytorch", "albert", "roberta", "gpt2"], "urls": [], "use_cases": ["speed up bert inference on cpu and gpu", "accelerate huggingface transformer models in production", "serve variable-length transformer batches without offline tuning", "run gpt2 decoder inference faster", "boost nlp services like faq matching and sentiment analysis", "replace tensorrt or onnx runtime for transformer serving"], "what_it_is": "A fast, user-friendly C++/Python runtime for transformer model inference (BERT, ALBERT, RoBERTa, GPT2, decoders) on CPU and GPU. It works as a PyTorch plugin, requiring only a few lines of code to accelerate Hugging Face transformer models with variable-length inputs and smart batching.", "when_to_avoid": ["you need the latest LLM architectures beyond classic encoder/decoder transformers", "you require a permissively licensed dependency (license is non-standard)", "you want a broadly maintained ecosystem - the project sees infrequent releases"], "when_to_choose": ["you need faster BERT/ALBERT/GPT2 inference than PyTorch with minimal code changes", "you serve variable-length inputs and want to avoid static-shape preprocessing", "you want both CPU and GPU acceleration from one runtime"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/turbotransformers", "repo": "Tencent/TurboTransformers", "role": "main", "score": 37}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.869682+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:25.391051+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb371dd4949ff57e82b2890d0bc2317b0d94b6c456a019d2109f98dd5dee7a68", "fetched_at": "2026-08-28T04:05:01.869682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent/TurboTransformers"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 32, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2326, "days_push": 411, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 37, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}