{"data":{"node":{"slug":"microsoft-pai","name":"pai","tagline":"Resource scheduling and cluster management for AI","github_url":"https://github.com/microsoft/pai","owner":"microsoft","repo":"pai","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"JavaScript","stars":2686,"forks":549,"topics":["ai","artificial-intelligence","chainer","cloud","cluster-management","cluster-manager","gpu","gpu-cluster","gpu-computing","gpu-scheduler","jupyter","kubernetes","machine-learning","model-training","on-premise","pytorch","resource-management","scheduling","tensorflow"],"archived":true,"github_pushed_at":"2024-06-06T07:56:07+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/microsoft-pai","markdown_url":"https://www.graphcanon.com/tools/microsoft-pai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-pai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-pai"},"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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"gpu","name":"gpu"},{"slug":"kubernetes","name":"kubernetes"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"pytorch","name":"pytorch"},{"slug":"resource-management","name":"resource-management"},{"slug":"scheduling","name":"scheduling"}],"edges":[],"neighbours":[{"slug":"skypilot-org-skypilot","name":"skypilot","tagline":"Run, manage, and scale AI workloads on any AI infrastructure.","github_url":"https://github.com/skypilot-org/skypilot","owner":"skypilot-org","repo":"skypilot","owner_avatar_url":"https://avatars.githubusercontent.com/u/109387420?v=4","primary_language":"Python","stars":10456,"forks":1175,"topics":["cloud-computing","cloud-management","cost-optimization","deep-learning","distributed-training","gpu","hyperparameter-tuning","job-queue","job-scheduler","llm-serving","llm-training","machine-learning","ml-infrastructure","ml-platform","mlops","multicloud","slurm","spot-instances","tpu"],"archived":false,"github_pushed_at":"2026-08-07T10:25:54+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/skypilot-org-skypilot","markdown_url":"https://www.graphcanon.com/tools/skypilot-org-skypilot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/skypilot-org-skypilot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=skypilot-org-skypilot","shared_categories":["model-training","inference-serving"]},{"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","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","shared_categories":["inference-serving"]},{"slug":"hyperopt-hyperopt","name":"hyperopt","tagline":"Distributed Asynchronous Hyperparameter Optimization in Python","github_url":"https://github.com/hyperopt/hyperopt","owner":"hyperopt","repo":"hyperopt","owner_avatar_url":"https://avatars.githubusercontent.com/u/5280805?v=4","primary_language":"Python","stars":7598,"forks":1075,"topics":["hacktoberfest"],"archived":false,"github_pushed_at":"2026-08-03T21:34:53+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/hyperopt-hyperopt","markdown_url":"https://www.graphcanon.com/tools/hyperopt-hyperopt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hyperopt-hyperopt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hyperopt-hyperopt","shared_categories":["model-training"]},{"slug":"tensorflow-serving","name":"serving","tagline":"A flexible, high-performance serving system for machine learning models","github_url":"https://github.com/tensorflow/serving","owner":"tensorflow","repo":"serving","owner_avatar_url":"https://avatars.githubusercontent.com/u/15658638?v=4","primary_language":"C++","stars":6359,"forks":2204,"topics":["cpp","deep-learning","deep-neural-networks","machine-learning","ml","neural-network","python","serving","tensorflow"],"archived":false,"github_pushed_at":"2026-07-30T07:02:43+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/tensorflow-serving","markdown_url":"https://www.graphcanon.com/tools/tensorflow-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorflow-serving","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorflow-serving","shared_categories":["inference-serving"]},{"slug":"kserve-kserve","name":"kserve","tagline":"Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes","github_url":"https://github.com/kserve/kserve","owner":"kserve","repo":"kserve","owner_avatar_url":"https://avatars.githubusercontent.com/u/83512434?v=4","primary_language":"Go","stars":5826,"forks":1632,"topics":["artificial-intelligence","cncf","genai","hacktoberfest","istio","k8s","knative","kserve","kubeflow","kubernetes","llm-inference","machine-learning","mlops","model-interpretability","model-serving","pytorch","service-mesh","tensorflow","vllm","xgboost"],"archived":false,"github_pushed_at":"2026-08-24T02:37:23+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/kserve-kserve","markdown_url":"https://www.graphcanon.com/tools/kserve-kserve.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kserve-kserve","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kserve-kserve","shared_categories":["inference-serving"]},{"slug":"gpustack-gpustack","name":"gpustack","tagline":"A GPU cluster manager for high-performance AI model serving and on-demand SSH-accessible GPU instances","github_url":"https://github.com/gpustack/gpustack","owner":"gpustack","repo":"gpustack","owner_avatar_url":"https://avatars.githubusercontent.com/u/169020824?v=4","primary_language":"Python","stars":5454,"forks":609,"topics":["ascend","cuda","deepseek","distributed-inference","genai","high-performance-inference","inference","llama","llm","llm-inference","llm-serving","maas","mindie","openai","qwen","rocm","sglang","vllm"],"archived":false,"github_pushed_at":"2026-08-07T03:09:44+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/gpustack-gpustack","markdown_url":"https://www.graphcanon.com/tools/gpustack-gpustack.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/gpustack-gpustack","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=gpustack-gpustack","shared_categories":["inference-serving"]},{"slug":"seldonio-seldon-core","name":"seldon-core","tagline":"An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models","github_url":"https://github.com/SeldonIO/seldon-core","owner":"SeldonIO","repo":"seldon-core","owner_avatar_url":"https://avatars.githubusercontent.com/u/10297834?v=4","primary_language":"Go","stars":4765,"forks":867,"topics":["aiops","deployment","kubernetes","machine-learning","machine-learning-operations","mlops","production-machine-learning","serving"],"archived":false,"github_pushed_at":"2026-03-23T11:39:54+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/seldonio-seldon-core","markdown_url":"https://www.graphcanon.com/tools/seldonio-seldon-core.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/seldonio-seldon-core","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=seldonio-seldon-core","shared_categories":["inference-serving"]},{"slug":"huaizhengzhang-ai-infra-from-zero-to-hero","name":"AI-Infra-from-Zero-to-Hero","tagline":"Awesome System for Machine Learning and LLM Infra","github_url":"https://github.com/HuaizhengZhang/AI-Infra-from-Zero-to-Hero","owner":"HuaizhengZhang","repo":"AI-Infra-from-Zero-to-Hero","owner_avatar_url":"https://avatars.githubusercontent.com/u/5894780?v=4","primary_language":null,"stars":4285,"forks":409,"topics":["ai-infra","genai","large-language-models","llmsys","mlsys","model-serving","model-training"],"archived":false,"github_pushed_at":"2025-07-25T02:24:35+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero","markdown_url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huaizhengzhang-ai-infra-from-zero-to-hero","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huaizhengzhang-ai-infra-from-zero-to-hero","shared_categories":["model-training","inference-serving"]},{"slug":"kubeflow-pipelines","name":"pipelines","tagline":"Machine Learning Pipelines for Kubeflow","github_url":"https://github.com/kubeflow/pipelines","owner":"kubeflow","repo":"pipelines","owner_avatar_url":"https://avatars.githubusercontent.com/u/33164907?v=4","primary_language":"Python","stars":4173,"forks":2075,"topics":["data-science","kubeflow","kubeflow-pipelines","kubernetes","machine-learning","mlops","pipeline"],"archived":false,"github_pushed_at":"2026-08-03T15:35:16+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/kubeflow-pipelines","markdown_url":"https://www.graphcanon.com/tools/kubeflow-pipelines.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kubeflow-pipelines","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kubeflow-pipelines","shared_categories":["model-training","inference-serving"]},{"slug":"lemony-ai-cascadeflow","name":"cascadeflow","tagline":"Optimized runtime for AI agents with cost and quality considerations.","github_url":"https://github.com/lemony-ai/cascadeflow","owner":"lemony-ai","repo":"cascadeflow","owner_avatar_url":"https://avatars.githubusercontent.com/u/169823043?v=4","primary_language":"Python","stars":4015,"forks":922,"topics":["agent","ai","anthropic","api","budgets","claude","cost-optimization","cost-transparency","google-adk","gpt","huggingface","llm","model-cascading","n8n","ollama","openai","python","together-ai","typescript","vllm"],"archived":false,"github_pushed_at":"2026-08-06T19:29:00+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/lemony-ai-cascadeflow","markdown_url":"https://www.graphcanon.com/tools/lemony-ai-cascadeflow.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lemony-ai-cascadeflow","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lemony-ai-cascadeflow","shared_categories":["model-training"]},{"slug":"b4rtaz-distributed-llama","name":"distributed-llama","tagline":"Distributed LLM inference using home devices cluster","github_url":"https://github.com/b4rtaz/distributed-llama","owner":"b4rtaz","repo":"distributed-llama","owner_avatar_url":"https://avatars.githubusercontent.com/u/12797776?v=4","primary_language":"C++","stars":3044,"forks":246,"topics":["distributed-computing","distributed-llm","llama2","llama3","llm","llm-inference","llms","neural-network","open-llm"],"archived":false,"github_pushed_at":"2026-07-05T16:47:20+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/b4rtaz-distributed-llama","markdown_url":"https://www.graphcanon.com/tools/b4rtaz-distributed-llama.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/b4rtaz-distributed-llama","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=b4rtaz-distributed-llama","shared_categories":["inference-serving"]},{"slug":"dstackai-dstack","name":"dstack","tagline":"Vendor-agnostic orchestration for AI workloads","github_url":"https://github.com/dstackai/dstack","owner":"dstackai","repo":"dstack","owner_avatar_url":"https://avatars.githubusercontent.com/u/54146142?v=4","primary_language":"Python","stars":2219,"forks":250,"topics":["agent-skills","agentic-orchestration","amd","cloud","containers","docker","fine-tuning","gpu","inference","k8s","kubernetes","llms","machine-learning","nvidia","orchestration","python","slurm","training"],"archived":false,"github_pushed_at":"2026-08-23T13:41:13+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/dstackai-dstack","markdown_url":"https://www.graphcanon.com/tools/dstackai-dstack.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dstackai-dstack","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dstackai-dstack","shared_categories":["model-training","inference-serving"]}]}}