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:Huggingface Datatrove Synthetic Data Generation
- Workflow:Openai Openai python Image Generation
- Workflow:Lance format Lance Version Management
- Workflow:Openai CLIP Zero shot image classification
- Workflow:Nautechsystems Nautilus trader Backtest with BacktestNode
- Workflow:Microsoft Semantic kernel Vector Store RAG Pipeline
- Workflow:Speechbrain Speechbrain Speech Enhancement Training
- Workflow:OpenHands OpenHands Conversation Lifecycle Management
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:Mage ai Mage ai SQL Database Source Extraction
Principles
- Principle:Ggml org Llama cpp Unicode Text Processing
- Principle:Langgenius Dify PaymentIntegration
- Principle:Mlflow Mlflow Model Loading
- Principle:LaurentMazare Tch rs Rotary Position Embedding
- Principle:PrefectHQ Prefect Asset Materialization
- Principle:Explodinggradients Ragas Prompt Persistence
- Principle:Confident ai Deepeval Package Constants Management
- Principle:Ggml org Ggml Backend Plugin Loading
- Principle:Huggingface Datasets TensorFlow Formatting
- Principle:Iamhankai Forest of Thought BFS Forest Solving
Implementations
- Implementation:Langgenius Dify UseDataSourceList
- Implementation:Rapidsai Cuml Traversal Forest
- Implementation:Ggml org Llama cpp Grammar
- Implementation:Liu00222 Open Prompt Injection eval helper
- Implementation:Langgenius Dify Service Fetch
- Implementation:CARLA simulator Carla Client Constructor
- Implementation:Fede1024 Rust rdkafka Rdkafka Sys Crate Root
- Implementation:VainF Torch Pruning BasePruner
- Implementation:Huggingface Transformers All Reduce Grads
- Implementation:Liu00222 Open Prompt Injection create task
Heuristics
- Heuristic:Speechbrain Speechbrain Nonfinite Loss Handling
- Heuristic:Apache Spark Hardware Provisioning Tips
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Langfuse Langfuse BullMQ Retry Strategy Patterns
- Heuristic:Norrrrrrr lyn WAInjectBench L2 Normalize CLIP Embeddings
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:ContextualAI HALOs LoRA Merge At Save
- Heuristic:Datajuicer Data juicer Checkpoint Resumption Strategy
- Heuristic:Openclaw Openclaw Retry With Exponential Backoff
- Heuristic:MarketSquare Robotframework browser Shared Node Process For Parallel
Environments
- Environment:Huggingface Trl DeepSpeed Environment
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Fede1024 Rust rdkafka CI Test Runner
- Environment:Openai Openai python Voice Helpers
- Environment:Langchain ai Langchain LangSmith Tracing Config
- Environment:Pola rs Polars Rust Build Environment
- Environment:Volcengine Verl Ray Distributed Environment
- Environment:Ray project Ray CI Build Matrix Environment
- Environment:Spotify Luigi Python Runtime