{"adoption": {"forks": 2694, "observed_at": "2026-08-28T04:11:07.099682+00:00", "stars": 14483}, "canonical_url": "https://ross.abutalabs.com/products/tensorrt-llm", "card": {"archived": false, "artifact_type": "library", "description": "TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.", "domain": ["large-language-models", "deep-learning", "gpu-computing", "artificial-intelligence"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning", "deep-learning", "sdk"], "health_score": 100, "homepage": "https://nvidia.github.io/TensorRT-LLM", "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["NVIDIA/TensorRT-LLM"], "name": "NVIDIA/TensorRT-LLM", "platform": ["python", "cpp"], "pushed_at": "2026-08-27T00:12:30+00:00", "repo": "NVIDIA/TensorRT-LLM", "stars": 14483, "tags": ["tensorrt", "nvidia", "inference-optimization", "llm-serving", "cuda-kernels", "mixture-of-experts", "multimodal", "openai-compatible-api", "linux", "gpu", "docker"], "topics": ["blackwell", "cuda", "moe", "pytorch", "llm-serving"], "urls": [], "use_cases": ["serve LLMs with high throughput on NVIDIA GPUs", "run optimized inference for models like DeepSeek or Llama", "deploy an OpenAI-compatible LLM server with trtllm-serve", "benchmark and evaluate LLM serving performance", "run multimodal and visual generation model inference", "optimize MoE model serving on Blackwell GPUs", "run offline batch inference with a Pythonic LLM API"], "what_it_is": "NVIDIA's TensorRT-LLM is a Python library and runtime for defining and serving Large Language Models with state-of-the-art inference optimizations on NVIDIA GPUs. It includes specialized kernels, an efficient orchestration runtime, and Python/C++ APIs for high-performance LLM deployment.", "when_to_avoid": ["you target non-NVIDIA hardware (AMD, Apple, CPU-only)", "you need a lightweight or simple inference setup", "you want to train or fine-tune models rather than serve them", "you need broad model coverage over raw speed"], "when_to_choose": ["you need maximum inference performance on NVIDIA GPUs", "you are serving LLMs in production at scale", "you want optimized kernels for MoE, quantization, or long-context models", "you need an OpenAI-compatible serving endpoint with metrics"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tensorrt-llm", "repo": "NVIDIA/TensorRT-LLM", "role": "main", "score": 84}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.099682+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:12:32.070493+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4d8cf633718340dd3a2bcf3f94ba9358232a241175cab31cfc2c325c6836b8b4", "fetched_at": "2026-08-28T04:11:07.099682+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/TensorRT-LLM"}, {"content_hash": "0c102a1fdc89ca8862adbdcf6aee5d38f79aee08cdeafe146383f014d53edf5d", "fetched_at": "2026-08-29T08:05:52.127738+00:00", "kind": "homepage", "missing": false, "url": "https://nvidia.github.io/TensorRT-LLM"}, {"content_hash": "030645afb9f266e5e3cb18fa93d489d9c6726bbdb6e6d76f1191d196e2c45e38", "fetched_at": "2026-08-29T08:05:52.130793+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tensorrt-llm/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 79, "rhythm": 68}, "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": 1113, "days_push": 7, "days_rel": 135, "gap_med": 39.0, "n_releases_24m": 15}, "score": 84, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}