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:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Allenai Open instruct DPO Preference Tuning
- Workflow:Astronomer Astronomer cosmos Watcher execution mode
- Workflow:Fede1024 Rust rdkafka Produce Consume Roundtrip
- Workflow:Huggingface Transformers Model Quantization
- Workflow:Datajuicer Data juicer Custom Operator Development
- Workflow:NVIDIA NeMo Aligner REINFORCE Training
- Workflow:Webdriverio Webdriverio Component Testing
- Workflow:Microsoft Onnxruntime Nodejs Inference
- Workflow:Apache Paimon Distributed Processing With Ray
Principles
- Principle:Datahub project Datahub Metadata Change Proposal
- Principle:Cleanlab Cleanlab Sklearn Compatible PyTorch Classifier
- Principle:Huggingface Transformers Sequence Packing
- Principle:Cypress io Cypress Configuration Validation
- Principle:OpenGVLab InternVL LoRA Adapter Injection
- Principle:Huggingface Alignment handbook Model Saving and Publishing
- Principle:Microsoft BIPIA Response Generation
- Principle:Datahub project Datahub Entity Read Modify
- Principle:Sdv dev SDV Column Distribution Visualization
- Principle:Tensorflow Serving HTTP Server Setup
Implementations
- Implementation:Lakeraai Pint benchmark Benchmark Results Interpretation
- Implementation:Mlc ai Web llm Tool Choice Request
- Implementation:Infiniflow Ragflow UseUserSettingRequest Hooks
- Implementation:Arize ai Phoenix Vignette Pnpm Lock
- Implementation:FMInference FlexLLMGen Batch Query Test
- Implementation:TobikoData Sqlmesh Story ModelNode
- Implementation:DistrictDataLabs Yellowbrick MissingDataVisualizer
- Implementation:Cypress io Cypress OpenModule Start Launchpad
- Implementation:Promptfoo Promptfoo initializeProject
- Implementation:EvolvingLMMs Lab Lmms eval TUI App Component
Heuristics
- Heuristic:Lance format Lance Vector Index Tuning
- Heuristic:Openai Openai node Warning Deprecated Assistants API
- Heuristic:Langfuse Langfuse Ingestion Date Boundary Delay
- Heuristic:HKUDS AI Trader Market Type Auto Detection
- Heuristic:SeldonIO Seldon core Model Load Timeout Tip
- Heuristic:Huggingface Transformers Label Smoothing Multi Label Warning
- Heuristic:Diagram of thought Diagram of thought Strict Vs Flexible Critic Rigor
- Heuristic:Lance format Lance Encoding Compression Thresholds
- Heuristic:Puppeteer Puppeteer Timeout Hierarchy
- Heuristic:PrefectHQ Prefect Task Timeout Thread Limitation
Environments
- Environment:Openai Openai agents python Voice Dependencies
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:Eventual Inc Daft AI Provider Dependencies
- Environment:Microsoft Onnxruntime Distributed Training Environment
- Environment:Sgl project Sglang CPU Runtime
- Environment:Online ml River Build Toolchain
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Openai Openai node WebSocket Dependency
- Environment:Mistralai Client python Realtime Transcription Environment
- Environment:ClickHouse ClickHouse Python3 Test Environment