{"data":{"slug":"ai-dynamo-dynamo","name":"dynamo","tagline":"A Datacenter Scale Distributed Inference Serving Framework","github_url":"https://github.com/ai-dynamo/dynamo","owner":"ai-dynamo","repo":"dynamo","owner_avatar_url":"https://avatars.githubusercontent.com/u/201626793?v=4","primary_language":"Rust","stars":7845,"forks":1486,"topics":["diffusion","disaggregated-serving","kubernetes","llm-inference","omni","routing-engine","rust","sglang","tensorrt-llm","vllm"],"archived":false,"github_pushed_at":"2026-08-24T17:59:43+00:00","maintenance_label":"Very active","stars_delta_30d":270,"url":"https://www.graphcanon.com/tools/ai-dynamo-dynamo","markdown_url":"https://www.graphcanon.com/tools/ai-dynamo-dynamo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ai-dynamo-dynamo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ai-dynamo-dynamo","description":"A Datacenter Scale Distributed Inference Serving Framework","homepage_url":"https://docs.nvidia.com/dynamo/latest","license":"Other","open_issues":1270,"watchers":72,"ai_summary":"Dynamo is a framework designed for large-scale distributed inference serving, primarily implemented in Rust and focusing on efficient handling of machine learning models.","readme_excerpt":"## Quick Start\n\n> This repo ships agent skills: if you work with an AI coding agent (Claude Code, Codex,\n> Cursor), clone the repo and ask it to deploy, troubleshoot, benchmark, or optimize a Dynamo\n> deployment. The skills activate automatically; no setup required.\n\n---\n\n### Option B: Install from PyPI\n\nInstall [uv](https://github.com/astral-sh/uv) (`curl -LsSf https://astral.sh/uv/install.sh | sh`), then:\n\n```bash\nuv pip install --prerelease=allow \"ai-dynamo[sglang]\"   # or [vllm]\n```\n\n> **Note:** TensorRT-LLM requires `pip` with `--extra-index-url https://pypi.nvidia.com`. See the [install guide](docs/fern/pages/cli/installation/install-dynamo.mdx) for TRT-LLM-specific instructions.\n\nThen start the frontend and a worker as shown above. See the [full installation guide](docs/fern/pages/cli/installation/install-dynamo.mdx) for system dependencies and backend-specific notes.\n\n---\n\n# Install system deps (Ubuntu 24.04)\nsudo apt install -y build-essential libhwloc-dev libudev-dev pkg-config libclang-dev protobuf-compiler python3-dev cmake\n\n---\n\n# Install Rust\ncurl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh && source $HOME/.cargo/env","github_created_at":"2025-03-03T18:40:07+00:00","created_at":"2026-07-11T11:42:23.991663+00:00","updated_at":"2026-08-24T18:00:46.812652+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"diffusion","name":"diffusion"},{"slug":"disaggregated-serving","name":"disaggregated-serving"},{"slug":"kubernetes","name":"kubernetes"},{"slug":"llm-inference","name":"llm-inference"},{"slug":"omni","name":"omni"},{"slug":"routing-engine","name":"routing-engine"},{"slug":"rust","name":"rust"},{"slug":"sglang","name":"sglang"}],"trust":{"provenance":{"is_fork":false,"github_id":942206898,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-24T18:00:45.636Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":16,"days_since_push":0,"last_release_at":"2026-08-22T17:07:43Z","stars_delta_30d":270,"open_issues_delta_30d":373},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:42:25.219Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-24T18:00:46.157Z"},"languages":{"value":["rust","python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-24T18:00:46.157Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-24T18:00:46.157Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you are working with high-throughput, low-latency requirements using Kubernetes.","For projects that leverage diffusion models or require disaggregated-serving capabilities."],"when_not_to_use":["If your project is not compatible with Rust and you face limitations in leveraging the dynamo's full potential without a strong Rust support team on hand.","In scenarios where fine-grained model management is less important than ease of use or when a more universally-supported language (like Python) is required."],"source":"enrich:decision_facts","observed_at":"2026-07-12T18:40:13.021Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Dynamo is a Rust-built framework for large-scale distributed inference serving, aimed at efficient management and deployment of machine learning models in a datacenter environment."}]}}