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:Eventual Inc Daft SQL Query Analytics
- Workflow:ArroyoSystems Arroyo Connection Setup
- Workflow:Sgl project Sglang Structured Output Generation
- Workflow:DevExpress Testcafe Basic Test Authoring
- Workflow:OpenRLHF OpenRLHF Math Reasoning Training
- Workflow:Iterative Dvc Pipeline Reproduction
- Workflow:Microsoft Agent framework Multi Agent Concurrent Orchestration
- Workflow:Langgenius Dify Plugin Installation and Configuration
- Workflow:Haotian liu LLaVA Single Image Inference
- Workflow:Apache Spark Standalone Cluster Deployment
Principles
- Principle:Ollama Ollama GGUF Model Conversion Olmo
- Principle:Diagram of thought Diagram of thought Task Requirements Definition
- Principle:ARISE Initiative Robosuite Action Vector Construction
- Principle:Haifengl Smile Spatial Index Construction
- Principle:Microsoft Playwright Analyze Test Execution
- Principle:FlagOpen FlagEmbedding Finetuned Reranker Validation
- Principle:Datajuicer Data juicer Overall Statistical Analysis
- Principle:Guardrails ai Guardrails Remote Guard Connection
- Principle:Arize ai Phoenix Experiment Evaluator Definition
- Principle:Liu00222 Open Prompt Injection Evaluation Pipeline
Implementations
- Implementation:DataTalksClub Data engineering zoomcamp Dlt Loading Method Selection
- Implementation:Unstructured IO Unstructured Unstructured Ingest CLI Processing
- Implementation:Pola rs Polars CategoricalMapping
- Implementation:Facebookresearch Habitat lab RunningMeanAndVar
- Implementation:Tensorflow Serving ServableVersionPolicy
- Implementation:OpenHands OpenHands Select
- Implementation:Run llama Llama index Docs Package Lock
- Implementation:HKUDS AI Trader BaseAgent Run Date Range
- Implementation:Anthropics Anthropic sdk python BetaToolComputerUse 20251124
- Implementation:AUTOMATIC1111 Stable diffusion webui Network restore weights
Heuristics
- Heuristic:Volcengine Verl Layered Summon Memory Tradeoff
- Heuristic:Norrrrrrr lyn WAInjectBench Union Ensemble Maximize Recall
- Heuristic:ARISE Initiative Robomimic HDF5 Cache Mode Selection
- Heuristic:HKUDS AI Trader A Share Lot Size Rule
- Heuristic:DataTalksClub Data engineering zoomcamp Dbt Materialization Strategy
- Heuristic:Norrrrrrr lyn WAInjectBench Balanced Class Weights Imbalanced Data
- Heuristic:Mlflow Mlflow Nested Run Organization
- Heuristic:Fede1024 Rust rdkafka Sensitive Config Sanitization
- Heuristic:Farama Foundation Gymnasium Action Space Normalization Tip
- Heuristic:Neuml Txtai MacOS Stability Workarounds
Environments
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:Bigscience workshop Petals Python Hivemind
- Environment:Mlc ai Web llm Node Build Toolchain
- Environment:Protectai Llm guard Python Runtime Dependencies
- Environment:Triton inference server Server TRT LLM Deployment
- Environment:CrewAIInc CrewAI Optional Provider Dependencies
- Environment:Axolotl ai cloud Axolotl Multi GPU
- Environment:Eventual Inc Daft AI Provider Dependencies
- Environment:DataExpert io Data engineer handbook Spark Iceberg Docker Environment
- Environment:Run llama Llama index Python LlamaIndex Core