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:Openai Openai agents python Guardrails Secured Agent
- Workflow:Microsoft Semantic kernel Agent Conversation And Orchestration
- Workflow:FlagOpen FlagEmbedding Embedder Inference
- Workflow:Lance format Lance Table Optimization
- Workflow:Openai Whisper Language Detection And Decoding
- Workflow:Lance format Lance Dataset Lifecycle
- Workflow:Bigscience workshop Petals Distributed Text Generation
- Workflow:Langchain ai Langgraph Building a Stateful Graph
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:Unstructured IO Unstructured Document Partitioning
Principles
- Principle:Tensorflow Serving Version Label Routing
- Principle:Turboderp org Exllamav2 Sampling Configuration
- Principle:Lance format Lance Full Text Query Execution
- Principle:OpenGVLab InternVL Weight Format Conversion
- Principle:CrewAIInc CrewAI Tool Execution And Monitoring
- Principle:Astronomer Astronomer cosmos Profile Configuration
- Principle:Unslothai Unsloth Model Merging And Saving
- Principle:Microsoft Agent framework Approval Request Presentation
- Principle:Anthropics Anthropic sdk python Beta Type System
- Principle:LaurentMazare Tch rs PyO3 Tensor Bridge
Implementations
- Implementation:Bigscience workshop Petals Distributed Evaluation Loop
- Implementation:FlagOpen FlagEmbedding MiniCPM Reranker Layerwise
- Implementation:Apache Airflow ListenerManager Hooks
- Implementation:OpenGVLab InternVL Classification Utils
- Implementation:Treeverse LakeFS Java SDK InternalApi
- Implementation:EvolvingLMMs Lab Lmms eval SciBench Utils
- Implementation:Online ml River Stats Var
- Implementation:Spotify Luigi RemoteTarget SSH
- Implementation:Explodinggradients Ragas MemorableNames Class
- Implementation:Helicone Helicone Health Check Tests
Heuristics
- Heuristic:Vespa engine Vespa Warning Deprecated Cloud API Constructors
- Heuristic:Microsoft BIPIA BF16 Compute Capability Check
- Heuristic:Mage ai Mage ai HTTP Request Timeout Defaults
- Heuristic:Pola rs Polars Avoid Lambda In Aggregation
- Heuristic:Google deepmind Dm control Rendering Backend Selection Tips
- Heuristic:Vllm project Vllm Attention Backend Selection
- Heuristic:Unslothai Unsloth Gradient Checkpointing Modes
- Heuristic:Nautechsystems Nautilus trader Order Rate Limiting Configuration
- Heuristic:Sdv dev SDV HMA Schema Simplification
- Heuristic:Truera Trulens Temperature Zero For Deterministic Scoring
Environments
- Environment:SeldonIO Seldon core GPU Inference Environment
- Environment:Vllm project Vllm AWS ECR
- Environment:Vibrantlabsai Ragas Python 3 9 Core Environment
- Environment:Dotnet Machinelearning Platform Architecture Support
- Environment:Evidentlyai Evidently Node Frontend Environment
- Environment:Fastai Fastbook NLP SpaCy Environment
- Environment:Microsoft Onnxruntime Sklearn Conversion Environment
- Environment:Princeton nlp SimPO CUDA Training
- Environment:Ray project Ray Python Runtime Environment
- Environment:Kserve Kserve Cert Manager