{"data":{"node":{"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":5710,"forks":650,"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":"2026-09-17T07:02:12+00:00","maintenance_label":"Very active","stars_delta_30d":256,"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"},"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":"ascend","name":"ascend"},{"slug":"cuda","name":"cuda"},{"slug":"deepseek","name":"deepseek"},{"slug":"distributed-inference","name":"distributed-inference"},{"slug":"genai","name":"genai"},{"slug":"high-performance-inference","name":"high-performance-inference"},{"slug":"inference","name":"inference"},{"slug":"llama","name":"llama"}],"edges":[],"neighbours":[{"slug":"lightning-ai-pytorch-lightning","name":"pytorch-lightning","tagline":"Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.","github_url":"https://github.com/Lightning-AI/pytorch-lightning","owner":"Lightning-AI","repo":"pytorch-lightning","owner_avatar_url":"https://avatars.githubusercontent.com/u/58386951?v=4","primary_language":"Python","stars":31363,"forks":3801,"topics":["ai","artificial-intelligence","data-science","deep-learning","machine-learning","python","pytorch"],"archived":false,"github_pushed_at":"2026-09-21T11:44:30+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/lightning-ai-pytorch-lightning","markdown_url":"https://www.graphcanon.com/tools/lightning-ai-pytorch-lightning.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lightning-ai-pytorch-lightning","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lightning-ai-pytorch-lightning","shared_categories":["inference-serving"]},{"slug":"physical-intelligence-openpi","name":"openpi","tagline":"Repository for running AI models with GPU requirements specified for inference and fine-tuning.","github_url":"https://github.com/Physical-Intelligence/openpi","owner":"Physical-Intelligence","repo":"openpi","owner_avatar_url":"https://avatars.githubusercontent.com/u/162759805?v=4","primary_language":"Python","stars":13874,"forks":2467,"topics":[],"archived":false,"github_pushed_at":"2026-08-24T16:27:13+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/physical-intelligence-openpi","markdown_url":"https://www.graphcanon.com/tools/physical-intelligence-openpi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/physical-intelligence-openpi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=physical-intelligence-openpi","shared_categories":["inference-serving"]},{"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":10568,"forks":1220,"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":"2026-09-05T16:25:57+00:00","maintenance_label":"Steady","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":["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":5970,"forks":1689,"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":"2026-09-19T13:08:33+00:00","maintenance_label":"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":"tensorchord-awesome-llmops","name":"Awesome-LLMOps","tagline":"An awesome & curated list of best LLMOps tools for developers","github_url":"https://github.com/tensorchord/Awesome-LLMOps","owner":"tensorchord","repo":"Awesome-LLMOps","owner_avatar_url":"https://avatars.githubusercontent.com/u/100543303?v=4","primary_language":"Shell","stars":5941,"forks":1058,"topics":["ai-development-tools","awesome-list","llmops","mlops"],"archived":false,"github_pushed_at":"2026-05-21T09:12:50+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/tensorchord-awesome-llmops","markdown_url":"https://www.graphcanon.com/tools/tensorchord-awesome-llmops.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorchord-awesome-llmops","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorchord-awesome-llmops","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":4782,"forks":866,"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":"pytorch-serve","name":"serve","tagline":"Serve, optimize and scale PyTorch models in production","github_url":"https://github.com/pytorch/serve","owner":"pytorch","repo":"serve","owner_avatar_url":"https://avatars.githubusercontent.com/u/21003710?v=4","primary_language":"Java","stars":4344,"forks":880,"topics":["cpu","deep-learning","docker","gpu","kubernetes","machine-learning","metrics","mlops","optimization","pytorch","serving"],"archived":true,"github_pushed_at":"2025-08-06T19:17:08+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/pytorch-serve","markdown_url":"https://www.graphcanon.com/tools/pytorch-serve.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pytorch-serve","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pytorch-serve","shared_categories":["inference-serving"]},{"slug":"nvidia-generativeaiexamples","name":"GenerativeAIExamples","tagline":"Generative AI reference workflows for accelerated infrastructure and microservice architecture","github_url":"https://github.com/NVIDIA/GenerativeAIExamples","owner":"NVIDIA","repo":"GenerativeAIExamples","owner_avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","primary_language":"Jupyter Notebook","stars":4149,"forks":1095,"topics":["gpu-acceleration","large-language-models","llm","llm-inference","microservice","nemo","rag","retrieval-augmented-generation","tensorrt","triton-inference-server"],"archived":false,"github_pushed_at":"2026-08-05T16:54:49+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/nvidia-generativeaiexamples","markdown_url":"https://www.graphcanon.com/tools/nvidia-generativeaiexamples.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-generativeaiexamples","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-generativeaiexamples","shared_categories":["inference-serving"]},{"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":3060,"forks":250,"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":"Slowing","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":"vllm-project-vllm-ascend","name":"vllm-ascend","tagline":"Community maintained hardware plugin for vLLM on Ascend","github_url":"https://github.com/vllm-project/vllm-ascend","owner":"vllm-project","repo":"vllm-ascend","owner_avatar_url":"https://avatars.githubusercontent.com/u/136984999?v=4","primary_language":"C++","stars":2854,"forks":2312,"topics":["ascend","inference","llm","llm-serving","llmops","mlops","model-serving","transformer","vllm"],"archived":false,"github_pushed_at":"2026-09-20T05:36:58+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/vllm-project-vllm-ascend","markdown_url":"https://www.graphcanon.com/tools/vllm-project-vllm-ascend.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/vllm-project-vllm-ascend","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=vllm-project-vllm-ascend","shared_categories":["inference-serving"]},{"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":2694,"forks":554,"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":false,"github_pushed_at":"2026-09-18T03:17:30+00:00","maintenance_label":"Active","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","shared_categories":["inference-serving"]},{"slug":"dstackai-dstack","name":"dstack","tagline":"Vendor-agnostic orchestration for training, inference and agentic 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":2253,"forks":262,"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":"2026-09-17T13:04:02+00:00","maintenance_label":"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":["inference-serving"]}]}}