{"data":{"node":{"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","stars_delta_30d":-6,"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"},"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":"cpu","name":"cpu"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"docker","name":"docker"},{"slug":"gpu","name":"gpu"},{"slug":"kubernetes","name":"kubernetes"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"metrics","name":"metrics"},{"slug":"mlops","name":"mlops"}],"edges":[],"neighbours":[{"slug":"alexsjones-llmfit","name":"llmfit","tagline":"Hardware-aware model recommendation tool","github_url":"https://github.com/AlexsJones/llmfit","owner":"AlexsJones","repo":"llmfit","owner_avatar_url":"https://avatars.githubusercontent.com/u/1235925?v=4","primary_language":"Rust","stars":36747,"forks":2329,"topics":["gguf","llm","localai","mlx","skill","unsloth"],"archived":false,"github_pushed_at":"2026-09-17T21:12:11+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/alexsjones-llmfit","markdown_url":"https://www.graphcanon.com/tools/alexsjones-llmfit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alexsjones-llmfit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alexsjones-llmfit","shared_categories":["inference-serving"]},{"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":"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":"huggingface-accelerate","name":"accelerate","tagline":"A tool for launching, training, and using PyTorch models with ease on various devices, configurations, including mixed precision support.","github_url":"https://github.com/huggingface/accelerate","owner":"huggingface","repo":"accelerate","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":9885,"forks":1513,"topics":[],"archived":false,"github_pushed_at":"2026-09-25T16:32:10+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-accelerate","markdown_url":"https://www.graphcanon.com/tools/huggingface-accelerate.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-accelerate","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-accelerate","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":"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":["inference-serving"]},{"slug":"superlinked-sie","name":"sie","tagline":"Open-source inference server and production cluster for all the models your agent needs.","github_url":"https://github.com/superlinked/sie","owner":"superlinked","repo":"sie","owner_avatar_url":"https://avatars.githubusercontent.com/u/94243920?v=4","primary_language":"Python","stars":3293,"forks":311,"topics":["bge","colbert","data-pipeline","deep-learning","embeddings","inference","inference-server","information-retrieval","llm","ml","mlops","natural-language-processing","nlp","python","reranking","retrieval","retrieval-augmented-generation","semantic-search","splade","vector-search"],"archived":false,"github_pushed_at":"2026-09-19T01:00:02+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/superlinked-sie","markdown_url":"https://www.graphcanon.com/tools/superlinked-sie.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/superlinked-sie","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=superlinked-sie","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":"ailia-ai-ailia-models","name":"ailia-models","tagline":"Repository of pre-trained AI models for ailia SDK","github_url":"https://github.com/ailia-ai/ailia-models","owner":"ailia-ai","repo":"ailia-models","owner_avatar_url":"https://avatars.githubusercontent.com/u/55011924?v=4","primary_language":"Python","stars":2392,"forks":365,"topics":["action-recognition","anomaly-detection","audio-processing","background-removal","crowd-counting","deep-learning","embeddings","face-detection","face-recognition","fashion-ai","gan","hand-detection","image-classification","image-segmentation","llm","neural-network","object-detection","object-recognition","object-tracking","pose-estimation"],"archived":false,"github_pushed_at":"2026-09-16T08:01:06+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/ailia-ai-ailia-models","markdown_url":"https://www.graphcanon.com/tools/ailia-ai-ailia-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ailia-ai-ailia-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ailia-ai-ailia-models","shared_categories":[]},{"slug":"tensorflow-model-optimization","name":"model-optimization","tagline":"Toolkit for optimizing ML models in Keras and TensorFlow","github_url":"https://github.com/tensorflow/model-optimization","owner":"tensorflow","repo":"model-optimization","owner_avatar_url":"https://avatars.githubusercontent.com/u/15658638?v=4","primary_language":"Python","stars":1579,"forks":348,"topics":["compression","deep-learning","keras","machine-learning","ml","model-compression","optimization","pruning","quantization","quantized-networks","quantized-neural-networks","quantized-training","sparsity","tensorflow"],"archived":false,"github_pushed_at":"2026-10-02T05:02:39+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/tensorflow-model-optimization","markdown_url":"https://www.graphcanon.com/tools/tensorflow-model-optimization.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorflow-model-optimization","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorflow-model-optimization","shared_categories":[]},{"slug":"arahim3-mlx-tune","name":"mlx-tune","tagline":"Fine-tune LLMs on your Mac with Apple Silicon for various tasks including SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR.","github_url":"https://github.com/ARahim3/mlx-tune","owner":"ARahim3","repo":"mlx-tune","owner_avatar_url":"https://avatars.githubusercontent.com/u/41390319?v=4","primary_language":"Python","stars":1412,"forks":92,"topics":["apple-silicon","deep-learning","huggingface","large-language-models","llm","llm-finetuning","local-llm","lora","machine-learning","macos","mlx","on-device-ai","peft","speech-recognition","speech-to-text","text-to-speech","transformers","unsloth","vision-language-model","whisper"],"archived":false,"github_pushed_at":"2026-06-23T12:24:30+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/arahim3-mlx-tune","markdown_url":"https://www.graphcanon.com/tools/arahim3-mlx-tune.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/arahim3-mlx-tune","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=arahim3-mlx-tune","shared_categories":[]},{"slug":"daoyuanli2816-can-i-finetune-this","name":"can-i-finetune-this","tagline":"Estimate if a Hugging Face model can fine-tune locally on GPU","github_url":"https://github.com/DaoyuanLi2816/can-i-finetune-this","owner":"DaoyuanLi2816","repo":"can-i-finetune-this","owner_avatar_url":"https://avatars.githubusercontent.com/u/94409450?v=4","primary_language":"Python","stars":792,"forks":107,"topics":["bitsandbytes","fine-tuning","gpu","hugging-face","llm","lora","memory-estimation","peft","pytorch","qlora","transformers","vram"],"archived":false,"github_pushed_at":"2026-07-23T05:11:25+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/daoyuanli2816-can-i-finetune-this","markdown_url":"https://www.graphcanon.com/tools/daoyuanli2816-can-i-finetune-this.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/daoyuanli2816-can-i-finetune-this","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=daoyuanli2816-can-i-finetune-this","shared_categories":[]}]}}