{"data":{"node":{"slug":"deepspeedai-deepspeed","name":"DeepSpeed","tagline":"Deep learning optimization library for efficient distributed training and inference","github_url":"https://github.com/deepspeedai/DeepSpeed","owner":"deepspeedai","repo":"DeepSpeed","owner_avatar_url":"https://avatars.githubusercontent.com/u/74068820?v=4","primary_language":"Python","stars":43065,"forks":4963,"topics":["billion-parameters","compression","data-parallelism","deep-learning","gpu","inference","machine-learning","mixture-of-experts","model-parallelism","pipeline-parallelism","pytorch","trillion-parameters","zero"],"archived":false,"github_pushed_at":"2026-09-06T16:52:55+00:00","maintenance_label":"Very active","stars_delta_30d":195,"url":"https://www.graphcanon.com/tools/deepspeedai-deepspeed","markdown_url":"https://www.graphcanon.com/tools/deepspeedai-deepspeed.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/deepspeedai-deepspeed","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=deepspeedai-deepspeed"},"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":"billion-parameters","name":"billion-parameters"},{"slug":"compression","name":"compression"},{"slug":"data-parallelism","name":"data-parallelism"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"gpu","name":"gpu"},{"slug":"inference","name":"inference"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"mixture-of-experts","name":"mixture-of-experts"}],"edges":[],"neighbours":[{"slug":"hpcaitech-colossalai","name":"ColossalAI","tagline":"Making large AI models cheaper, faster and more accessible","github_url":"https://github.com/hpcaitech/ColossalAI","owner":"hpcaitech","repo":"ColossalAI","owner_avatar_url":"https://avatars.githubusercontent.com/u/88699314?v=4","primary_language":"Python","stars":41443,"forks":4496,"topics":["ai","big-model","data-parallelism","deep-learning","distributed-computing","foundation-models","heterogeneous-training","hpc","inference","large-scale","model-parallelism","pipeline-parallelism"],"archived":false,"github_pushed_at":"2026-08-31T17:52:00+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/hpcaitech-colossalai","markdown_url":"https://www.graphcanon.com/tools/hpcaitech-colossalai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hpcaitech-colossalai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hpcaitech-colossalai","shared_categories":["model-training","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":["model-training","inference-serving"]},{"slug":"horovod-horovod","name":"horovod","tagline":"Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.","github_url":"https://github.com/horovod/horovod","owner":"horovod","repo":"horovod","owner_avatar_url":"https://avatars.githubusercontent.com/u/46361271?v=4","primary_language":"Python","stars":14682,"forks":2232,"topics":["baidu","deep-learning","deeplearning","keras","machine-learning","machinelearning","mpi","mxnet","pytorch","ray","spark","tensorflow","uber"],"archived":true,"github_pushed_at":"2026-09-17T09:15:03+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/horovod-horovod","markdown_url":"https://www.graphcanon.com/tools/horovod-horovod.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/horovod-horovod","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=horovod-horovod","shared_categories":["model-training"]},{"slug":"nvidia-tensorrt-llm","name":"TensorRT-LLM","tagline":"Python API for defining and optimizing Large Language Models for efficient inference on NVIDIA GPUs","github_url":"https://github.com/NVIDIA/TensorRT-LLM","owner":"NVIDIA","repo":"TensorRT-LLM","owner_avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","primary_language":"Python","stars":14645,"forks":2756,"topics":["blackwell","cuda","llm-serving","moe","pytorch"],"archived":false,"github_pushed_at":"2026-09-18T07:58:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/nvidia-tensorrt-llm","markdown_url":"https://www.graphcanon.com/tools/nvidia-tensorrt-llm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-tensorrt-llm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-tensorrt-llm","shared_categories":["model-training","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":["model-training","inference-serving"]},{"slug":"deepspeedai-deepspeed-mii","name":"DeepSpeed-MII","tagline":"Enables low-latency and high-throughput inference for deep learning models","github_url":"https://github.com/deepspeedai/DeepSpeed-MII","owner":"deepspeedai","repo":"DeepSpeed-MII","owner_avatar_url":"https://avatars.githubusercontent.com/u/74068820?v=4","primary_language":"Python","stars":2113,"forks":192,"topics":["deep-learning","inference","pytorch"],"archived":false,"github_pushed_at":"2025-06-30T16:21:45+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/deepspeedai-deepspeed-mii","markdown_url":"https://www.graphcanon.com/tools/deepspeedai-deepspeed-mii.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/deepspeedai-deepspeed-mii","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=deepspeedai-deepspeed-mii","shared_categories":["inference-serving"]},{"slug":"invergent-ai-surogate","name":"surogate","tagline":"Training/Fine-tuning at the speed of light","github_url":"https://github.com/invergent-ai/surogate","owner":"invergent-ai","repo":"surogate","owner_avatar_url":"https://avatars.githubusercontent.com/u/233052289?v=4","primary_language":"C++","stars":813,"forks":10,"topics":["cuda","deep-learning","fine-tuning","generative-ai","llama","llm","llms","nvidia-gpu","qwen","sft"],"archived":false,"github_pushed_at":"2026-09-19T02:29:57+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/invergent-ai-surogate","markdown_url":"https://www.graphcanon.com/tools/invergent-ai-surogate.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/invergent-ai-surogate","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=invergent-ai-surogate","shared_categories":["model-training"]},{"slug":"tencent-forward","name":"Forward","tagline":"A library for high performance deep learning inference on NVIDIA GPUs","github_url":"https://github.com/Tencent/Forward","owner":"Tencent","repo":"Forward","owner_avatar_url":"https://avatars.githubusercontent.com/u/18461506?v=4","primary_language":"C++","stars":557,"forks":63,"topics":["cuda","deep-learning","forward","gpu","inference","inference-engine","keras","neural-network","onnx","pytorch","tensorflow","tensorrt"],"archived":false,"github_pushed_at":"2022-01-29T16:34:05+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/tencent-forward","markdown_url":"https://www.graphcanon.com/tools/tencent-forward.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tencent-forward","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tencent-forward","shared_categories":["inference-serving"]}]}}