{"adoption": {"forks": 1830, "observed_at": "2026-08-28T04:10:44.752594+00:00", "stars": 10939}, "canonical_url": "https://ross.abutalabs.com/products/server", "card": {"archived": false, "artifact_type": "service", "description": "The Triton Inference Server provides an optimized cloud and edge inferencing solution. ", "domain": ["machine-learning", "deep-learning", "large-language-models", "cloud-computing", "developer-tools", "self-hosted"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning", "http-server", "rpc", "gpu-computing", "monitoring"], "health_score": 100, "homepage": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html", "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "stable", "member_repos": ["triton-inference-server/server"], "name": "triton-inference-server/server", "platform": ["cloud", "self-hosted", "cross-platform"], "pushed_at": "2026-08-26T20:29:13+00:00", "repo": "triton-inference-server/server", "stars": 10939, "tags": ["inference-server", "model-serving", "nvidia", "tensorrt", "pytorch", "onnx", "batching", "grpc", "edge-deployment", "model-repository", "linux", "docker", "gpu"], "topics": ["inference", "gpu", "machine-learning", "deep-learning", "cloud", "datacenter", "edge"], "urls": [], "use_cases": ["serve pytorch models in production with a rest api", "deploy llm like llama2 or phi-3 with vllm or tensorrt-llm backend", "run batched gpu inference for many models from one server", "host onnx models for real-time inference at the edge", "serve models over grpc with dynamic batching and ensembles", "deploy models on nvidia gpus in docker containers", "stream audio or video inference requests to a model server"], "what_it_is": "NVIDIA Triton Inference Server is an open-source inference serving software that deploys AI models from multiple frameworks (TensorRT, PyTorch, ONNX, OpenVINO, Python, vLLM, and more) behind HTTP/REST and gRPC APIs. It supports cloud, data center, edge, and embedded deployments on NVIDIA GPUs, x86/ARM CPUs, and AWS Inferentia, with dynamic batching, ensembles, and streaming inference.", "when_to_avoid": ["you only need simple CPU-only inference for a single small model", "you want a lightweight embedded inference runtime rather than a server", "your stack is tightly tied to a non-NVIDIA accelerator without supported backends"], "when_to_choose": ["you need production-grade, high-throughput model serving on NVIDIA GPUs", "you must serve models from multiple frameworks through a single API", "you want dynamic batching, model ensembles, and streaming out of the box", "you deploy across cloud, data center, and edge with the same tooling"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/server", "repo": "triton-inference-server/server", "role": "main", "score": 98}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.752594+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:17:19.703074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e48d0e50b083607df8fac2d93db09848d91a5a56eb8785f60d78de225696acb9", "fetched_at": "2026-08-28T04:10:44.752594+00:00", "kind": "readme", "missing": false, "url": "https://github.com/triton-inference-server/server"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.741500+00:00", "kind": "homepage", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"}, {"content_hash": "ff5abf6672e7d3e8ef9bbf55cee2a027aadc352738663c471e32628ac27f752d", "fetched_at": "2026-08-29T08:16:13.744204+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/contents.html"}, {"content_hash": "e844fdedbdc28a0bac486e0f1dcfd4091d928c9b2e88f20c48163834a1f39976", "fetched_at": "2026-08-29T08:16:13.745861+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/index.html"}, {"content_hash": "e4821debe26225154225117eededf0ab72b8122babd955d2d30d22cccd71c46f", "fetched_at": "2026-08-29T08:16:13.747509+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/release_notes.html"}, {"content_hash": "dcbe515801cd186afaa601d0489fb50478471046c794bb6b8bbf1f9c7ee6f33a", "fetched_at": "2026-08-29T08:16:13.749184+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/introduction/compatibility.html"}, {"content_hash": "27d18f71d91fc3c1a841c8fb02901bc1090dc8232c152c38975596a8c5bbd51b", "fetched_at": "2026-08-29T08:16:13.751066+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quick_deployment.html"}, {"content_hash": "0c3e84f637c21652002847cca20b4c11a966fb69a1634351a406a2284924e641", "fetched_at": "2026-08-29T08:16:13.752496+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html"}, {"content_hash": "9cb4d4bcbc75f122448a44ffaf97b4f232daac1020776f53188dea6afa56632e", "fetched_at": "2026-08-29T08:16:13.754308+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/llm.html"}, {"content_hash": "53cec4a5d0c3281211876f92d6724a33c2351dd07cbbfaa3ae8524ac162976c5", "fetched_at": "2026-08-29T08:16:13.756969+00:00", "kind": "site_page", "missing": false, "url": "https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/tutorials/Popular_Models_Guide/Llama2/vllm_guide.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 95}, "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": 2890, "days_push": 7, "days_rel": 35, "gap_med": 28.0, "n_releases_24m": 23}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}