{"data":{"node":{"slug":"ovg-project-kvcached","name":"kvcached","tagline":"Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond","github_url":"https://github.com/ovg-project/kvcached","owner":"ovg-project","repo":"kvcached","owner_avatar_url":"https://avatars.githubusercontent.com/u/213673672?v=4","primary_language":"Python","stars":1424,"forks":165,"topics":["elastic-kvcache","gpu-mutiplexing","gpu-sharing","inference-engine","kvcache","kvcache-optimization","kvcached","llm","llm-framework","llm-inference","llm-serving","ollama","online-offline-coserve","serverless","sglang","vllm"],"archived":false,"github_pushed_at":"2026-09-18T19:17:57+00:00","maintenance_label":"Very active","stars_delta_30d":309,"url":"https://www.graphcanon.com/tools/ovg-project-kvcached","markdown_url":"https://www.graphcanon.com/tools/ovg-project-kvcached.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ovg-project-kvcached","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ovg-project-kvcached"},"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":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"elastic-kvcache","name":"elastic-kvcache"},{"slug":"gpu-sharing","name":"gpu-sharing"},{"slug":"kvcache","name":"kvcache"},{"slug":"llm-inference","name":"llm-inference"}],"edges":[],"neighbours":[{"slug":"mem0ai-mem0","name":"mem0","tagline":"Drop-in memory infrastructure for AI agents and apps","github_url":"https://github.com/mem0ai/mem0","owner":"mem0ai","repo":"mem0","owner_avatar_url":"https://avatars.githubusercontent.com/u/137054526?v=4","primary_language":"Python","stars":65557,"forks":7690,"topics":["agentic-memory","agentic-memory-system","agents","ai","ai-agents","chatgpt","genai","llm","long-term-memory","memory","memory-management","python","rag","state-management"],"archived":false,"github_pushed_at":"2026-09-18T08:17:57+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/mem0ai-mem0","markdown_url":"https://www.graphcanon.com/tools/mem0ai-mem0.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mem0ai-mem0","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mem0ai-mem0","shared_categories":[]},{"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":"zilliztech-gptcache","name":"GPTCache","tagline":"Semantic cache for LLMs, integrated with LangChain and llama_index.","github_url":"https://github.com/zilliztech/GPTCache","owner":"zilliztech","repo":"GPTCache","owner_avatar_url":"https://avatars.githubusercontent.com/u/18416694?v=4","primary_language":"Python","stars":8194,"forks":595,"topics":["aigc","autogpt","babyagi","chatbot","chatgpt","chatgpt-api","dolly","gpt","langchain","llama","llama-index","llm","memcache","milvus","openai","redis","semantic-search","similarity-search","vector-search"],"archived":false,"github_pushed_at":"2025-07-11T09:04:36+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/zilliztech-gptcache","markdown_url":"https://www.graphcanon.com/tools/zilliztech-gptcache.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zilliztech-gptcache","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zilliztech-gptcache","shared_categories":["llm-frameworks"]},{"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":8121,"forks":1601,"topics":["diffusion","disaggregated-serving","kubernetes","llm-inference","omni","routing-engine","rust","sglang","tensorrt-llm","vllm"],"archived":false,"github_pushed_at":"2026-09-19T17:01:54+00:00","maintenance_label":"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":"linkedin-liger-kernel","name":"Liger-Kernel","tagline":"Efficient Triton Kernels for LLM Training","github_url":"https://github.com/linkedin/Liger-Kernel","owner":"linkedin","repo":"Liger-Kernel","owner_avatar_url":"https://avatars.githubusercontent.com/u/357098?v=4","primary_language":"Python","stars":6600,"forks":593,"topics":["finetuning","gemma2","hacktoberfest","llama","llama3","llm-training","llms","mistral","phi3","triton","triton-kernels"],"archived":false,"github_pushed_at":"2026-09-03T15:56:18+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/linkedin-liger-kernel","markdown_url":"https://www.graphcanon.com/tools/linkedin-liger-kernel.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/linkedin-liger-kernel","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=linkedin-liger-kernel","shared_categories":[]},{"slug":"flashinfer-ai-flashinfer","name":"flashinfer","tagline":"FlashInfer is a kernel library for serving large language models","github_url":"https://github.com/flashinfer-ai/flashinfer","owner":"flashinfer-ai","repo":"flashinfer","owner_avatar_url":"https://avatars.githubusercontent.com/u/145061914?v=4","primary_language":"Cuda","stars":6452,"forks":1472,"topics":["attention","cuda","distributed-inference","gpu","jit","large-large-models","llm-inference","moe","nvidia","pytorch"],"archived":false,"github_pushed_at":"2026-09-19T01:31:07+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/flashinfer-ai-flashinfer","markdown_url":"https://www.graphcanon.com/tools/flashinfer-ai-flashinfer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/flashinfer-ai-flashinfer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=flashinfer-ai-flashinfer","shared_categories":["llm-frameworks","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":"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":"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":"kubeflow-trainer","name":"trainer","tagline":"Distributed AI Model Training and LLM Fine-Tuning on Kubernetes","github_url":"https://github.com/kubeflow/trainer","owner":"kubeflow","repo":"trainer","owner_avatar_url":"https://avatars.githubusercontent.com/u/33164907?v=4","primary_language":"Go","stars":2225,"forks":1052,"topics":["ai","distributed","fine-tuning","gpu","huggingface","jax","kubeflow","kubernetes","llm","machine-learning","mlops","python","pytorch","tensorflow","xgboost"],"archived":false,"github_pushed_at":"2026-09-19T02:01:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/kubeflow-trainer","markdown_url":"https://www.graphcanon.com/tools/kubeflow-trainer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kubeflow-trainer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kubeflow-trainer","shared_categories":["llm-frameworks"]},{"slug":"beam-cloud-beta9","name":"beta9","tagline":"Ultrafast serverless GPU inference, sandboxes, and background jobs","github_url":"https://github.com/beam-cloud/beta9","owner":"beam-cloud","repo":"beta9","owner_avatar_url":"https://avatars.githubusercontent.com/u/126977053?v=4","primary_language":"Go","stars":1783,"forks":165,"topics":["autoscaler","cloudrun","cuda","developer-productivity","distributed-computing","faas","fine-tuning","functions-as-a-service","generative-ai","gpu","large-language-models","llm","llm-inference","ml-platform","paas","self-hosted","serverless","serverless-containers"],"archived":false,"github_pushed_at":"2026-09-19T18:15:33+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/beam-cloud-beta9","markdown_url":"https://www.graphcanon.com/tools/beam-cloud-beta9.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/beam-cloud-beta9","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=beam-cloud-beta9","shared_categories":["llm-frameworks","inference-serving"]},{"slug":"tensorflow-mesh","name":"mesh","tagline":"Mesh TensorFlow: Model Parallelism Made Easier","github_url":"https://github.com/tensorflow/mesh","owner":"tensorflow","repo":"mesh","owner_avatar_url":"https://avatars.githubusercontent.com/u/15658638?v=4","primary_language":"Python","stars":1630,"forks":255,"topics":[],"archived":true,"github_pushed_at":"2023-11-17T19:39:54+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/tensorflow-mesh","markdown_url":"https://www.graphcanon.com/tools/tensorflow-mesh.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorflow-mesh","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorflow-mesh","shared_categories":[]}]}}