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:Langchain ai Langgraph Building a Stateful Graph
- Workflow:Apache Dolphinscheduler Datasource Plugin Development
- Workflow:OpenGVLab InternVL LoRA Finetuning
- Workflow:Microsoft Playwright AI agent driven testing
- Workflow:Apache Beam Local Pipeline Execution
- Workflow:Spotify Luigi Database Ingestion Pipeline
- Workflow:Protectai Llm guard LLM Input Output Scanning
- Workflow:CARLA simulator Carla Building from Source
- Workflow:OpenBMB UltraFeedback Completion Generation
- Workflow:Sdv dev SDV Constrained synthesis
Principles
- Principle:Huggingface Diffusers Prior Preservation Training
- Principle:Online ml River Pipeline Composition
- Principle:Ggml org Llama cpp ResourceManagement
- Principle:Duckdb Duckdb HTTP Communication
- Principle:Triton inference server Server TRT LLM Environment Setup
- Principle:Langgenius Dify Pipeline Publishing
- Principle:Pyro ppl Pyro Conjugate Bayesian Updates
- Principle:Deepspeedai DeepSpeed Async IO Operations
- Principle:Ollama Ollama Chat Template System
- Principle:Cohere ai Cohere python Input Text Preparation
Implementations
- Implementation:Iterative Dvc Stage Run
- Implementation:Datajuicer Data juicer Monitor
- Implementation:Lakeraai Pint benchmark Pint Benchmark Function
- Implementation:Interpretml Interpret Powerlift InsecureDocker
- Implementation:LLMBook zh LLMBook zh github io Apply Rotary Pos Emb
- Implementation:Huggingface Optimum Backend Specific Pipeline
- Implementation:ARISE Initiative Robosuite CompositionalRobots
- Implementation:Open compass VLMEvalKit SArena Mini Utils
- Implementation:Apache Druid StringMenuItems
- Implementation:Dotnet Machinelearning FastTree LambdaMART Derivatives
Heuristics
- Heuristic:Gretelai Gretel synthetics Mixed Precision Training Tradeoff
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Spcl Graph of thoughts Backoff Retry On API Errors
- Heuristic:Eventual Inc Daft Execution Config Tuning
- Heuristic:Langgenius Dify Credential Sanitization In API Responses
- Heuristic:Snorkel team Snorkel NLP Preprocessor Memoization
- Heuristic:Bigscience workshop Petals KV Cache Sizing For Attention Types
- Heuristic:Ucbepic Docetl Reduce Parallel Fold Tuning
- Heuristic:Lance format Lance Encoding Compression Thresholds
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
Environments
- Environment:Lm sys FastChat API Keys And Credentials
- Environment:Huggingface Datasets PyTorch Integration
- Environment:ARISE Initiative Robomimic HuggingFace Hub Dependencies
- Environment:PacktPublishing LLM Engineers Handbook Unsloth Finetuning Environment
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:Norrrrrrr lyn WAInjectBench Conda Python 39 CUDA Environment
- Environment:Microsoft DeepSpeedExamples SuperOffload Runtime
- Environment:Intel Ipex llm RAG LangChain Environment
- Environment:LaurentMazare Tch rs Libtorch Build Environment