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:SeleniumHQ Selenium Browser Session Setup
- Workflow:Mbzuai oryx Awesome LLM Post training Awesome List Curation
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Entry Development
- Workflow:Wandb Weave Evaluation Pipeline
- Workflow:Evidentlyai Evidently Monitoring Dashboard Setup
- Workflow:Evidentlyai Evidently LLM Evaluation Monitoring
- Workflow:MaterializeInc Materialize dbt Integration
- Workflow:OpenGVLab InternVL Benchmark Evaluation
- Workflow:Iamhankai Forest of Thought FoT Benchmark Evaluation
- Workflow:Datahub project Datahub Docker Quickstart Deployment
Principles
- Principle:OpenGVLab InternVL Distributed Evaluation
- Principle:Openclaw Openclaw Onboarding Wizard
- Principle:Allenai Open instruct DPO Loss Dispatch
- Principle:Explodinggradients Ragas Metric Baseline Correlation
- Principle:OpenGVLab InternVL Flash Attention Optimization
- Principle:Apache Kafka Release Notes Generation
- Principle:Datahub project Datahub Entity Retrieval
- Principle:Duckdb Duckdb Function Registration Generation
- Principle:Apache Spark Release Finalization
- Principle:MarketSquare Robotframework browser Release Publication
Implementations
- Implementation:Huggingface Datasets JaxFormatter
- Implementation:Mlc ai Mlc llm Text Streamer Py
- Implementation:SeleniumHQ Selenium Pnpm Lock
- Implementation:Ollama Ollama Llama Model Apertus
- Implementation:Openai Openai node ChatCompletionCreateParams
- Implementation:Apache Druid TimeMenuItems
- Implementation:Protectai Llm guard Input Code
- Implementation:Infiniflow Ragflow Settings Init Settings
- Implementation:Online ml River Stats EWVar
- Implementation:Ollama Ollama Readline History
Heuristics
- Heuristic:MaterializeInc Materialize Pipeline Test Trimming Rules
- Heuristic:Intel Ipex llm NF4 Quantization Best Practice
- Heuristic:Pytorch Serve Torch Compile Best Practices
- Heuristic:Openai Evals Chat Format Recommendation
- Heuristic:Gretelai Gretel synthetics Parallel Generation CUDA Disable
- Heuristic:VainF Torch Pruning AutoGrad Dependency Graph
- Heuristic:Alibaba MNN LLM Runtime Tuning
- Heuristic:Turboderp org Exllamav2 Attention Backend Selection
- Heuristic:Online ml River HST Feature Scaling Requirement
- Heuristic:ClickHouse ClickHouse ThinLTO Build Tradeoffs
Environments
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment
- Environment:Ggml org Ggml CUDA GPU Environment
- Environment:Microsoft Agent framework API Credentials
- Environment:Puppeteer Puppeteer Cross Platform Browser Environment
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:Apache Kafka Gradle Build Environment
- Environment:Kserve Kserve Gateway API
- Environment:OpenGVLab InternVL PyTorch CUDA
- Environment:Marker Inc Korea AutoRAG VLLM Environment
- Environment:Farama Foundation Gymnasium Python 3 10 Runtime