{"adoption": {"forks": 103, "observed_at": "2026-08-28T04:03:19.531032+00:00", "stars": 1037}, "canonical_url": "https://ross.abutalabs.com/products/optimum-nvidia", "card": {"archived": false, "artifact_type": "library", "description": null, "domain": ["large-language-models", "machine-learning", "gpu-computing"], "enriched": true, "function": ["llm-inference", "machine-learning", "sdk"], "health_score": 82, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "experimental", "member_repos": ["huggingface/optimum-nvidia"], "name": "huggingface/optimum-nvidia", "platform": ["python"], "pushed_at": "2026-05-26T10:32:41+00:00", "repo": "huggingface/optimum-nvidia", "stars": 1037, "tags": ["tensorrt-llm", "nvidia", "hugging-face", "transformers", "fp8", "text-generation", "linux", "gpu", "docker"], "topics": [], "urls": [], "use_cases": ["run LLM inference faster on NVIDIA GPUs", "accelerate text generation with TensorRT-LLM", "use fp8 quantization for LLM inference", "drop-in replacement for transformers pipelines", "serve LLaMA models at high tokens/second", "optimize Hugging Face models for Hopper and Ampere GPUs"], "what_it_is": "Optimum-NVIDIA is a Python library that bridges Hugging Face Transformers with NVIDIA TensorRT-LLM for highly optimized LLM inference on NVIDIA GPUs. It lets users run models like LLaMA 2 significantly faster by changing a single line in existing transformers code.", "when_to_avoid": ["you are not on NVIDIA GPUs or Linux", "you need a stable, mature production library", "you want CPU or multi-vendor GPU inference"], "when_to_choose": ["you already use Hugging Face transformers and want faster inference on NVIDIA GPUs", "you need maximum LLM throughput with minimal code changes", "you run on Linux with CUDA 12.6 and supported NVIDIA hardware"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/optimum-nvidia", "repo": "huggingface/optimum-nvidia", "role": "main", "score": 58}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:19.531032+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:04:23.561841+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b105ce36597b2b9590b7c4e85414520db0f8becd6116f78f4086537ddf8616da", "fetched_at": "2026-08-28T04:03:19.531032+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-nvidia"}, {"content_hash": "fcdc36032fdd12fb49f307f49b9873fd38dfdd6dda3f3a8497917356005596ef", "fetched_at": "2026-08-29T13:05:31.726492+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-nvidia/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 84, "longevity": 75, "rhythm": 16}, "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": 1062, "days_push": 99, "days_rel": 587, "gap_med": 128, "n_releases_24m": 2}, "score": 58, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}