We will introduce all knowledges of artificial intelligence system infrastructure.
本文试图构建AI基础设施领域的知识 Roadmap 学习路线图。
- volcano: A Cloud Native Batch System
- koordinator: QoS based scheduling system for hybrid orchestration workloads on Kubernetes, bringing workloads the best layout and status.
- kserve: Standardized Serverless ML Inference Platform on Kubernetes
- triton: an open-source inference serving software
- Horovod: Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
- fluid: an open source Kubernetes-native Distributed Dataset Orchestrator and Accelerator for data-intensive applications, such as big data and AI applications.
- kubeDL: Run your deep learning workloads on Kubernetes more easily and efficiently.