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:Gretelai Gretel synthetics LSTM Text Generation
- Workflow:Duckdb Duckdb Benchmark Execution
- Workflow:Fastai Fastbook NLP Text Classification
- Workflow:LLMBook zh LLMBook zh github io Inference and Quantization
- Workflow:Predibase Lorax OpenAI Chat Completion
- Workflow:EvolvingLMMs Lab Lmms eval End to End Evaluation
- Workflow:Sdv dev SDV Constrained synthesis
- Workflow:Zai org CogVideo Video Editing DDIM Inversion
- Workflow:Ollama Ollama Custom Model Creation
- Workflow:Neuml Txtai Semantic Search
Principles
- Principle:AnswerDotAI RAGatouille Semantic Search
- Principle:OpenBMB UltraFeedback Score Validation and Correction
- Principle:Mlc ai Web llm Chrome Extension Manifest
- Principle:Tensorflow Serving Executor Abstraction
- Principle:EvolvingLMMs Lab Lmms eval MCP Tool Calling
- Principle:Huggingface Datasets Hub Config Verification
- Principle:Mlflow Mlflow Prompt Alias Management
- Principle:Cohere ai Cohere python Bedrock Client Initialization
- Principle:Sdv dev SDV Constraint Validation
- Principle:Promptfoo Promptfoo Interactive Project Setup
Implementations
- Implementation:Haosulab ManiSkill GoogleRobot
- Implementation:Eventual Inc Daft DataFrame Select
- Implementation:Open compass VLMEvalKit MEGABench Evaluator
- Implementation:Predibase Lorax NeoX Modeling
- Implementation:ClickHouse ClickHouse Defines
- Implementation:Guardrails ai Guardrails ValidatorServiceBase
- Implementation:LaurentMazare Tch rs Sparse Adam
- Implementation:Microsoft DeepSpeedExamples BingBert Tokenization
- Implementation:Openclaw Openclaw HealthCommand And ProbeGateway
- Implementation:Ggml org Llama cpp CLIP Model
Heuristics
- Heuristic:Zai org CogVideo Decord Import Order Bug
- Heuristic:Langgenius Dify Extension Initialization Order
- Heuristic:LMCache LMCache Chunk Size And Default Config
- Heuristic:Mlc ai Mlc llm GPU Memory Budget Tuning
- Heuristic:Astronomer Astronomer cosmos Memory Optimised Imports
- Heuristic:DataTalksClub Data engineering zoomcamp CSV Chunk Size Optimization
- Heuristic:Explodinggradients Ragas Retry And Backoff Configuration
- Heuristic:OpenGVLab InternVL Pixel Shuffle Downsampling
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
- Heuristic:Dotnet Machinelearning Sparsity Threshold Optimization
Environments
- Environment:Marker Inc Korea AutoRAG API Keys And Credentials
- Environment:Heibaiying BigData Notes Java 8 Maven Environment
- Environment:Hiyouga LLaMA Factory Distributed Training Environment
- Environment:Huggingface Datatrove Slurm Cluster Environment
- Environment:Marker Inc Korea AutoRAG API Keys Configuration
- Environment:LLMBook zh LLMBook zh github io Data Processing Environment
- Environment:Openclaw Openclaw Mintlify Documentation Platform
- Environment:Marker Inc Korea AutoRAG VLLM Environment
- Environment:Haifengl Smile Java 25 Runtime
- Environment:OpenGVLab InternVL PEFT LoRA