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:Mlc ai Mlc llm Model Compilation
- Workflow:Mage ai Mage ai SQL Database Source Extraction
- Workflow:Kserve Kserve Deploying InferenceService
- Workflow:Google deepmind Dm control Composer Environment Building
- Workflow:Risingwavelabs Risingwave Sink Connector Pipeline
- Workflow:Sail sg LongSpec Long Context Evaluation
- Workflow:Nightwatchjs Nightwatch Programmatic API Usage
- Workflow:MarketSquare Robotframework browser Browser Test Authoring
- Workflow:Openclaw Openclaw Multi Agent Routing
- Workflow:VainF Torch Pruning CNN Pruning
Principles
- Principle:MarketSquare Robotframework browser ES2015 Module Transpilation
- Principle:Datahub project Datahub UI Access
- Principle:Testtimescaling Testtimescaling github io Paper Relevance Assessment
- Principle:Iamhankai Forest of Thought Majority Vote Consensus
- Principle:LLMBook zh LLMBook zh github io Training Loop Execution
- Principle:Nightwatchjs Nightwatch Session Cleanup
- Principle:Run llama Llama index Text Chunking
- Principle:Farama Foundation Gymnasium Environment Interaction Loop
- Principle:Pola rs Polars Multi Format Data Writing
- Principle:LMCache LMCache CacheBlend Connector Initialization
Implementations
- Implementation:Langfuse Langfuse DashboardService Types
- Implementation:Huggingface Transformers Quantization Verification Pattern
- Implementation:Marker Inc Korea AutoRAG Generate QA Ragas
- Implementation:Avhz RustQuant Power Backend
- Implementation:Sktime Pytorch forecasting NBeats From Dataset
- Implementation:NVIDIA DALI Paddle ResNet Model
- Implementation:Openai Openai node Beta Realtime Resource
- Implementation:Hpcaitech ColossalAI BaseModel
- Implementation:Openai Openai python Response Prompt
- Implementation:SeleniumHQ Selenium HasCapabilities
Heuristics
- Heuristic:Langgenius Dify SSE Streaming Error Handling
- Heuristic:Liu00222 Open Prompt Injection Attack Effectiveness Hierarchy
- Heuristic:Dagster io Dagster Retry Strategy Configuration
- Heuristic:Intel Ipex llm Use Cache Training Vs Inference
- Heuristic:Tensorflow Serving Resource Estimation Rules
- Heuristic:Apache Dolphinscheduler JDBC Security Blocklist
- Heuristic:Apache Spark Warning Deprecated DStream Streaming
- Heuristic:NVIDIA TransformerEngine FP8 Recipe Auto Selection
- Heuristic:Marker Inc Korea AutoRAG Deterministic Evaluation Generation
- Heuristic:Mlflow Mlflow Prompt Cache Tuning
Environments
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:Shiyu coder Kronos Comet ML Logging
- Environment:Norrrrrrr lyn WAInjectBench Conda Python 39 CUDA Environment
- Environment:Langgenius Dify Redis And Celery Environment
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:Open compass VLMEvalKit API Keys And Credentials
- Environment:Tencent Ncnn Build Environment
- Environment:Protectai Llm guard ONNX Runtime Acceleration
- Environment:Langchain ai Langchain Anthropic API Credentials
- Environment:Iamhankai Forest of Thought OpenAI API Credentials