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:Sail sg LongSpec GLIDE Draft Model Training
- Workflow:Spcl Graph of thoughts Custom GoT Use Case Integration
- Workflow:Dagster io Dagster Modal Serverless Pipeline
- Workflow:AnswerDotAI RAGatouille In Memory Retrieval
- Workflow:Puppeteer Puppeteer Browser Installation And Management
- Workflow:Fastai Fastbook Collaborative Filtering
- Workflow:Deepset ai Haystack Hybrid Document Search
- Workflow:Langgenius Dify Docker Deployment
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Mlc ai Web llm Chrome Extension Integration
Principles
- Principle:SqueezeAILab ETS Answer Extraction
- Principle:CrewAIInc CrewAI MCP Server Connection
- Principle:Farama Foundation Gymnasium REINFORCE Policy Gradient
- Principle:Tencent Ncnn Instance Segmentation
- Principle:Volcengine Verl GAE Advantage Estimation
- Principle:FMInference FlexLLMGen BFloat16 Mixed Precision Optimization
- Principle:FlowiseAI Flowise Role Based Access Control
- Principle:Sdv dev SDV HMA Synthesis
- Principle:Cleanlab Cleanlab Segmentation Label Issue Filtering
- Principle:Vespa engine Vespa Java Bootstrap and Maven Build
Implementations
- Implementation:Infiniflow Ragflow Knowledge Constants
- Implementation:FlagOpen FlagEmbedding RetroMAE Data
- Implementation:Kserve Kserve Alibi Helper
- Implementation:Huggingface Datatrove GopherQualityFilter
- Implementation:NVIDIA NeMo Curator IDGenerator
- Implementation:Datajuicer Data juicer ImageFaceCountFilter
- Implementation:ContextualAI HALOs Alignment Trainers
- Implementation:NVIDIA TransformerEngine PyTorch Quantizer Cpp
- Implementation:Eventual Inc Daft Decode Image
- Implementation:Mlflow Mlflow Database CLI
Heuristics
- Heuristic:ArroyoSystems Arroyo Parallelism Configuration
- Heuristic:Togethercomputer Together python Retry Backoff Strategy
- Heuristic:Lucidrains X transformers Flash Attention Configuration
- Heuristic:Openai Evals Event Batching Configuration
- Heuristic:Roboflow Rf detr Batch Size Memory Tradeoff
- Heuristic:LaurentMazare Tch rs Safetensors Format Preference
- Heuristic:Testtimescaling Testtimescaling github io Hardcoded IDs vs Registry
- Heuristic:Ollama Ollama Multimodal Parallel Restriction
- Heuristic:PeterL1n BackgroundMattingV2 Backbone Scale Selection
- Heuristic:Sdv dev SDV Sampling Retry Tuning
Environments
- Environment:Marker Inc Korea AutoRAG API Keys And Credentials
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:Apache Dolphinscheduler Database Backend
- Environment:FlowiseAI Flowise Docker Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Duckdb Duckdb Release Publishing Env
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:ArroyoSystems Arroyo Object Storage
- Environment:Apache Spark Kubernetes Runtime
- Environment:Mit han lab Llm awq Python Runtime Environment