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:OWASP Www project top 10 for large language model applications GenAI Red Team Testing
- Workflow:Duckdb Duckdb Building From Source
- Workflow:Protectai Modelscan CLI Model Scanning
- Workflow:NVIDIA TransformerEngine FSDP Distributed Training
- Workflow:SqueezeAILab ETS Answer Evaluation Pipeline
- Workflow:Bitsandbytes foundation Bitsandbytes FSDP QLoRA Distributed Training
- Workflow:OpenGVLab InternVL Benchmark Evaluation
- Workflow:ARISE Initiative Robosuite Human Demonstration Collection
- Workflow:Neuml Txtai Agent Orchestration
- Workflow:NVIDIA TransformerEngine Comm GEMM Overlap Training
Principles
- Principle:Togethercomputer Together python Endpoint Management
- Principle:Microsoft Autogen Tool Execution Loop
- Principle:Recommenders team Recommenders Spark Evaluation Metrics
- Principle:Kubeflow Pipelines Reusable Component Loading
- Principle:Pola rs Polars Group By Key Definition
- Principle:Webdriverio Webdriverio XML Processing
- Principle:Langchain ai Langchain Retriever Integration
- Principle:Trailofbits Fickling Benchmark Payload Injection
- Principle:Pyro ppl Pyro Discrete Posterior Decoding
- Principle:CrewAIInc CrewAI Agent Configuration
Implementations
- Implementation:Langgenius Dify UseMetadata
- Implementation:MarketSquare Robotframework browser Translation CLI
- Implementation:Alibaba MNN TestMNNFromOnnx
- Implementation:Avhz RustQuant Order
- Implementation:Turboderp org Exllamav2 Hadamard
- Implementation:CrewAIInc CrewAI CrewAI RAG Adapter
- Implementation:Speechbrain Speechbrain Train RescueSpeech
- Implementation:Openclaw Openclaw RunEmbeddedPiAgent
- Implementation:Langgenius Dify Error Parser
- Implementation:Apache Airflow Metrics Template
Heuristics
- Heuristic:Unstructured IO Unstructured PDF Element Sorting
- Heuristic:Rapidsai Cuml CUDA Kernel Caching
- Heuristic:Allenai Open instruct Gradient Clipping Norm
- Heuristic:Dotnet Machinelearning LDA Thread Reservation
- Heuristic:Nautechsystems Nautilus trader Parquet Row Group Tuning
- Heuristic:Apache Hudi Data Skipping Limitations
- Heuristic:Haifengl Smile Platform Native Library Selection
- Heuristic:Teamcapybara Capybara Async Waiting And Retry
- Heuristic:Lance format Lance Encoding Compression Thresholds
- Heuristic:Microsoft Agent framework Declaration Only Tools Pattern
Environments
- Environment:Ucbepic Docetl Docker Deployment
- Environment:Apache Paimon Optional Extensions
- Environment:Kserve Kserve Istio Service Mesh
- Environment:Cleanlab Cleanlab Python Core Environment
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Sgl project Sglang Performance Dashboard
- Environment:MaterializeInc Materialize Docker Compose Runtime
- Environment:Unstructured IO Unstructured All Docs
- Environment:Treeverse LakeFS Spark GC Environment
- Environment:Duckdb Duckdb Code Formatting Tools