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:PrefectHQ Prefect Web Scraping Pipeline
- Workflow:Langfuse Langfuse Prompt management lifecycle
- Workflow:LLMBook zh LLMBook zh github io Data Preprocessing Pipeline
- Workflow:Marker Inc Korea AutoRAG Evaluation Data Creation
- Workflow:Microsoft Autogen Multi Agent Conversation
- Workflow:PrefectHQ Prefect Dbt Model Orchestration
- Workflow:Datajuicer Data juicer Distributed Ray Processing
- Workflow:DataExpert io Data engineer handbook Dimensional Data Modeling Environment Setup
- Workflow:SeldonIO Seldon core Model Explainability
- Workflow:Turboderp org Exllamav2 LoRA Adapter Inference
Principles
- Principle:Datahub project Datahub Action Pipeline Configuration
- Principle:LaurentMazare Tch rs Atari Environment Preprocessing
- Principle:Mage ai Mage ai API Stream Discovery
- Principle:Microsoft Autogen Graph Construction
- Principle:Webdriverio Webdriverio Service Worker Pattern
- Principle:NVIDIA NeMo Curator Scene Detection and Clipping
- Principle:Microsoft Onnxruntime Source Framework Training
- Principle:Huggingface Optimum Sequential Block Quantization
- Principle:Langgenius Dify Docker Infrastructure
- Principle:OpenBMB UltraFeedback Principle Sampling
Implementations
- Implementation:SeleniumHQ Selenium Closure Functions
- Implementation:Mit han lab Llm awq LLaVA Conversation
- Implementation:Volcengine Verl Toolcall Shaping Reward
- Implementation:Run llama Llama index EvaluatorEvaluationDataset
- Implementation:Nautechsystems Nautilus trader BacktestNode Run
- Implementation:CrewAIInc CrewAI ContextualAI Query Tool
- Implementation:Ucbepic Docetl PromptImprovementDialog
- Implementation:Facebookresearch Habitat lab ActionSpace
- Implementation:LMCache LMCache CacheGen Decoder
- Implementation:Run llama Llama index StorageContext Persist
Heuristics
- Heuristic:Lakeraai Pint benchmark Chunking Stride 25 Percent Overlap
- Heuristic:BerriAI Litellm Cooldown Threshold Tuning
- Heuristic:Tencent Ncnn Lightmode Memory Optimization
- Heuristic:NVIDIA TransformerEngine Attention Backend Selection
- Heuristic:Mlc ai Web llm KV Cache Window Configuration
- Heuristic:OpenRLHF OpenRLHF vLLM Embedding Resize Warning
- Heuristic:Getgauge Taiko Implicit Wait Tuning
- Heuristic:Ray project Ray NaN Score Filtering In PBT
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:Webdriverio Webdriverio Default Timeout Configuration
Environments
- Environment:Kubeflow Pipelines Python SDK
- Environment:Hiyouga LLaMA Factory Optional Inference Backends
- Environment:Hiyouga LLaMA Factory Distributed Training Environment
- Environment:Open compass VLMEvalKit Data Storage Environment
- Environment:Deepspeedai DeepSpeed CPU Environment
- Environment:Langchain ai Langgraph Docker Deployment Environment
- Environment:Ggml org Ggml Metal GPU Environment
- Environment:NVIDIA TransformerEngine Python PyTorch Requirements
- Environment:Infiniflow Ragflow Frontend Node Environment
- Environment:Apache Kafka JVM Runtime Environment