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 Dolphinscheduler Datasource Plugin Development
- Workflow:Microsoft Onnxruntime Python Inference Pipeline
- Workflow:CrewAIInc CrewAI Flow Based Orchestration
- Workflow:SqueezeAILab ETS ETS Experiment Pipeline
- Workflow:Trailofbits Fickling Pickle Decompilation and Tracing
- Workflow:Nightwatchjs Nightwatch Custom Commands And Assertions
- Workflow:Webdriverio Webdriverio Cloud Service Integration
- Workflow:Langchain ai Langgraph Human in the Loop Agent
- Workflow:Volcengine Verl Supervised Fine Tuning
- Workflow:Google research Deduplicate text datasets Single file deduplication
Principles
- Principle:Webdriverio Webdriverio Configuration Management
- Principle:Turboderp org Exllamav2 Vision Tower Loading
- Principle:Eventual Inc Daft Row Counting
- Principle:Arize ai Phoenix OTel Dependency Setup
- Principle:Iterative Dvc Experiment Result Capture
- Principle:Ucbepic Docetl Entity Link Resolution
- Principle:Langgenius Dify Component Testing
- Principle:Microsoft Playwright Define Agent Actions with Perform
- Principle:Apache Flink Compaction Request Triggering
- Principle:Farama Foundation Gymnasium Space Abstraction
Implementations
- Implementation:Microsoft Autogen FunctionTool Init
- Implementation:Mit han lab Llm awq VILA15 Demo
- Implementation:Avhz RustQuant DateRollingConvention
- Implementation:Haosulab ManiSkill Merge Trajectories Func
- Implementation:Ollama Ollama Llama Vocab Types
- Implementation:SeleniumHQ Selenium ScriptKey
- Implementation:Tencent Ncnn Arcface Example
- Implementation:Eventual Inc Daft AI Embed Image
- Implementation:Microsoft DeepSpeedExamples Create Critic Model
- Implementation:Huggingface Peft Constants
Heuristics
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:Microsoft BIPIA Delta Weight CPU Loading
- Heuristic:Apache Dolphinscheduler Netty Thread Sizing
- Heuristic:TobikoData Sqlmesh Snapshot TTL Defaults
- Heuristic:AnswerDotAI RAGatouille Collection Size Index Tuning
- Heuristic:Liu00222 Open Prompt Injection Defense Strategy Selection
- Heuristic:Mit han lab Llm awq Kernel Selection Thresholds
- Heuristic:Triton inference server Server Dynamic Batching Tuning
- Heuristic:Mage ai Mage ai HTTP Error Classification
- Heuristic:Kserve Kserve Prefix Cache Consistency
Environments
- Environment:Getgauge Taiko Node Runtime
- Environment:OpenRLHF OpenRLHF Ray Distributed Environment
- Environment:Pytorch Serve vLLM Engine Environment
- Environment:Pytorch Serve DeepSpeed Environment
- Environment:Langchain ai Langgraph Docker Deployment Environment
- Environment:Promptfoo Promptfoo Provider API Keys
- Environment:Spcl Graph of thoughts OpenAI API Access
- Environment:OWASP Www project top 10 for large language model applications PR Description Generator Runtime
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:Infiniflow Ragflow Docker Infrastructure