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:Langchain ai Langchain Streaming Responses
- Workflow:Openai Evals Running an eval set
- Workflow:Huggingface Trl Supervised Finetuning
- Workflow:Apache Shardingsphere Cluster Mode Initialization
- Workflow:Turboderp org Exllamav2 Interactive Chat
- Workflow:Huggingface Open r1 Model Evaluation
- Workflow:FlagOpen FlagEmbedding Benchmark Evaluation
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:Guardrails ai Guardrails LLM Output Validation
- Workflow:Sail sg LongSpec GLIDE Draft Model Training
Principles
- Principle:Huggingface Datatrove Text Encoding Repair
- Principle:Apache Paimon Type System
- Principle:Microsoft Playwright Implement Response Fixtures
- Principle:Eventual Inc Daft Data Preprocessing Image Decoding
- Principle:Nautechsystems Nautilus trader Data Configuration Schema
- Principle:Obss Sahi Model Weight Download
- Principle:Ggml org Llama cpp Input Provenance Tracking
- Principle:Scikit learn Scikit learn Column Composition
- Principle:Protectai Modelscan Unsafe Operator Detection
- Principle:LaurentMazare Tch rs ImageNet Preprocessing
Implementations
- Implementation:Run llama Llama index SQLTableNodeMapping
- Implementation:Triton inference server Server GenerateDocs
- Implementation:NVIDIA DALI PyTorch Output Integration
- Implementation:Openai Openai node Node ESM Web Lockfile
- Implementation:Allenai Open instruct Layer Init
- Implementation:Haifengl Smile Decomposition Solvers
- Implementation:Apache Flink SourceReaderOptions
- Implementation:NVIDIA TransformerEngine Ops Sequential
- Implementation:Duckdb Duckdb Extension Sign
- Implementation:FlowiseAI Flowise Input
Heuristics
- Heuristic:Tensorflow Serving Warning Deprecated CreateTfrtSavedModel Raw
- Heuristic:DataExpert io Data engineer handbook Watermark Late Arrival Tolerance
- Heuristic:Allenai Open instruct Disable Dropout In RL
- Heuristic:Huggingface Alignment handbook Sequence Packing Strategy
- Heuristic:Langchain ai Langchain Retry Scope Best Practice
- Heuristic:Huggingface Diffusers Memory Offloading Strategy
- Heuristic:HKUDS AI Trader Linear Retry Backoff
- Heuristic:Nightwatchjs Nightwatch Timeout And Retry Tuning
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Apache Dolphinscheduler Failover Marker TTL
Environments
- Environment:Langchain ai Langgraph Python Runtime Environment
- Environment:Elevenlabs Elevenlabs python Python Httpx
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:Microsoft Autogen Python Runtime Environment
- Environment:Microsoft Agent framework Python 3 10 Runtime
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:OpenRLHF OpenRLHF DeepSpeed Environment
- Environment:MaterializeInc Materialize Dbt Materialize Runtime
- Environment:Sail sg LongSpec Training Environment
- Environment:Lakeraai Pint benchmark Python 310 With Transformers