Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:Apache Paimon Table Read Write
- Workflow:Langfuse Langfuse Batch export pipeline
- Workflow:MaterializeInc Materialize CI Pipeline Generation
- Workflow:Interpretml Interpret Blackbox Model Explanation
- Workflow:Hiyouga LLaMA Factory PPO RLHF Training
- Workflow:Googleapis Python genai Model Fine Tuning
- Workflow:HKUDS AI Trader Data Pipeline
- Workflow:CarperAI Trlx RLHF Dialogue Alignment
- Workflow:Hpcaitech ColossalAI LLaMA Continual Pretraining
Principles
- Principle:Microsoft Playwright Create Test with Agent Fixture
- Principle:Pyro ppl Pyro Advanced ELBO Estimators
- Principle:Unstructured IO Unstructured Time Profiling
- Principle:Microsoft Agent framework Python Workspace Configuration
- Principle:NVIDIA NeMo Aligner Reward Model Architecture Selection
- Principle:Pola rs Polars Data Type Transformation
- Principle:Vespa engine Vespa Log Target and Level Configuration
- Principle:Helicone Helicone Result Type Pattern
- Principle:Huggingface Datatrove CSV Data Reading
- Principle:Facebookresearch Habitat lab Hierarchical Policy Assembly
Implementations
- Implementation:Lm sys FastChat Preprocess Conversation
- Implementation:Open compass VLMEvalKit EgoExoBench Utils
- Implementation:Openai Openai agents python Non Strict Output Type Pattern
- Implementation:Microsoft Semantic kernel HuggingFace TextGeneration TestData
- Implementation:Datajuicer Data juicer Quality Classifier Train
- Implementation:Togethercomputer Together python Text Preprocessing Pattern
- Implementation:Apache Dolphinscheduler UI Dependency Lockfile
- Implementation:Open compass VLMEvalKit Emu
- Implementation:BerriAI Litellm Callback Configs
- Implementation:ARISE Initiative Robosuite CompositionalRobots
Heuristics
- Heuristic:Togethercomputer Together python Multipart Upload Strategy
- Heuristic:CARLA simulator Carla Behavior Agent Profiles
- Heuristic:Tencent Ncnn Letterbox Vs Direct Resize
- Heuristic:Alibaba ROLL PPO Clipping Defaults
- Heuristic:Volcengine Verl FSDP Mixed Precision Init
- Heuristic:Deepset ai Haystack Pipeline Max Runs Safety Limit
- Heuristic:Cleanlab Cleanlab KNN Distance Metric Selection
- Heuristic:Danijar Dreamerv3 Adaptive Gradient Clipping
- Heuristic:Google deepmind Dm control Prop Settling Physics Tuning
- Heuristic:Astronomer Astronomer cosmos Watcher Queue Sizing
Environments
- Environment:NVIDIA NeMo Curator Video Codec Stack
- Environment:Protectai Llm guard Python Runtime Dependencies
- Environment:FlowiseAI Flowise Database Environment
- Environment:Pyro ppl Pyro Visualization Tools
- Environment:Apache Hudi Flink Runtime Environment
- Environment:Volcengine Verl Ray Distributed Environment
- Environment:Googleapis Python genai Python 3 10 SDK Runtime
- Environment:Openai Openai node OpenAI API Credentials
- Environment:Kserve Kserve Knative Serving
- Environment:Avhz RustQuant Rust Stable