Generals

Articles

Awesome Repositories

  • awesome-mlops: A curated list of references for MLOps
  • AI-Infra: init to record my learning path of AI Infra, especially on inference.
  • AI-Infra-from-Zero-to-Hero: πŸš€ Awesome System for Machine Learning ⚑️ AI System Papers and Industry Practice
  • Awesome-LLMOps: An awesome & curated list of best LLMOps tools for developers

Blogs

Code Example / Crash Course

Landscape

Topics

MLOps Tools (Curious Version πŸ”­)

MLOps Toolkits

  • KitOps: An open source DevOps tool for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI artifact.
  • polyaxon: MLOps Tools For Managing & Orchestrating The Machine Learning LifeCycle

Model Management & Deployment

  • KServe: A standardΒ Model Inference PlatformΒ onΒ Kubernetes, built forΒ highly scalableΒ use cases.
  • MLServer: An open source inference server for your machine learning models.
  • gpustack: Simple, scalable AI model deployment on GPU clusters
  • openvino: OpenVINOβ„’ is an open-source toolkit for optimizing and deploying AI inference

LLM Gateway

  • PortKey: A blazing fast AI Gateway with integrated guardrails
  • higress: πŸ€– AI Gateway | AI Native API Gateway

MLOps Tools

Compute Engine & Serving

  • Ray: an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads. 🌟 (Recommended)
  • vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
  • onnxruntime: cross-platform, high performance ML inferencing and training accelerator

Model Management & Deployment

  • MLFlow: Open source platform for the machine learning lifecycle 🌟 (Recommended)

LLM Gateway

  • litellm: Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format 🌟 (Recommended)

VectorDB

  • Chroma: The AI-native open-source vector database (Opensource) 🌟 (Recommended)
  • Milvus: A high-performance, highly scalable vector database that runs efficiently across a wide range of environments, from a laptop to large-scale distributed systems 🌟 (Recommended)