Main Page
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:Apache Paimon Data Ingestion With Ray Sink
- Workflow:Google deepmind Mujoco Simulation benchmarking
- Workflow:BerriAI Litellm SDK Completion
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
- Workflow:Alibaba MNN LLM Deployment Pipeline
- Workflow:Cohere ai Cohere python Model Finetuning
- Workflow:OpenHands OpenHands Third Party Runtime Integration
- Workflow:Elevenlabs Elevenlabs python Voice Cloning
- Workflow:Heibaiying BigData Notes Kafka Producer Consumer Pipeline
- Workflow:Mistralai Client python GCP Chat Completion
Principles
- Principle:Farama Foundation Gymnasium Vector Episode Statistics
- Principle:Kubeflow Pipelines Conditional Branching
- Principle:Langchain ai Langchain Input Preparation
- Principle:Groq Groq python Text Embedding Request
- Principle:Isaac sim IsaacGymEnvs Assembly Sub Policy Training
- Principle:Arize ai Phoenix Batch Span Annotation
- Principle:Pola rs Polars Input Data Preparation
- Principle:Roboflow Rf detr Model Deployment
- Principle:Tensorflow Serving Kubernetes Cluster Creation
- Principle:Langchain ai Langgraph Pregel Execution Algorithm
Implementations
- Implementation:Mlc ai Mlc llm CLI Main
- Implementation:Facebookresearch Habitat lab ActionEmbedding
- Implementation:NVIDIA TransformerEngine MXFP8 Storage
- Implementation:Open compass VLMEvalKit QSpatial Utils
- Implementation:Facebookresearch Audiocraft MultiPeriodDiscriminator
- Implementation:Webdriverio Webdriverio BrowserStack Launcher Tunnel
- Implementation:Apache Shardingsphere DatabaseRuleConfigurationManager Refresh
- Implementation:Online ml River Metrics SMAPE
- Implementation:Apache Airflow PercentFormatRender
- Implementation:LaurentMazare Tch rs Darknet Builder
Heuristics
- Heuristic:Openai Openai agents python Default Max Turns Safety Limit
- Heuristic:Datajuicer Data juicer Operator Fusion Rules
- Heuristic:Openclaw Openclaw WebSocket Reconnection And Session Cleanup
- Heuristic:Openai CLIP L2 Normalization For Cosine Similarity
- Heuristic:LLMBook zh LLMBook zh github io LoRA Initialization Strategy
- Heuristic:Huggingface Alignment handbook DDP Bias Buffer Ignore
- Heuristic:PeterL1n BackgroundMattingV2 Backbone Scale Selection
- Heuristic:Openai Openai node Browser Safety Guard
- Heuristic:Mit han lab Llm awq Kernel Selection Thresholds
- Heuristic:AUTOMATIC1111 Stable diffusion webui VRAM Management Strategies
Environments
- Environment:OpenHands OpenHands Frontend Build Environment
- Environment:Eventual Inc Daft Ray Distributed Runner
- Environment:Risingwavelabs Risingwave Docker Deployment Environment
- Environment:Huggingface Alignment handbook Python Datasets
- Environment:Lakeraai Pint benchmark Python 310 With Pandas
- Environment:Ucbepic Docetl Python Runtime
- Environment:Obss Sahi Python Detection Frameworks
- Environment:Volcengine Verl vLLM Rollout Environment
- Environment:Huggingface Datasets SQL Dependencies
- Environment:Anthropics Anthropic sdk python Azure Foundry Environment