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:Microsoft LoRA LoRA Integration
- Workflow:Openai Openai node Audio Processing
- Workflow:Getgauge Taiko Interactive Test Recording
- Workflow:Nautechsystems Nautilus trader Strategy development
- Workflow:LaurentMazare Tch rs MNIST Training
- Workflow:NVIDIA NeMo Curator Text Curation Pipeline
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:Facebookresearch Habitat lab HITL Interactive Evaluation
- Workflow:Obss Sahi Sliced Inference Pipeline
- Workflow:Puppeteer Puppeteer Web Scraping And Interaction
Principles
- Principle:Apache Airflow Security Review Planning
- Principle:Protectai Llm guard Scanner Benchmarking
- Principle:Facebookresearch Audiocraft Audio Dataset Preparation
- Principle:Diagram of thought Diagram of thought System Prompt Configuration
- Principle:ChenghaoMou Text dedup Substring Deduplication
- Principle:Sdv dev SDV Synthesizer Persistence
- Principle:Langgenius Dify Build Pipeline
- Principle:Onnx Onnx External Data Saving
- Principle:Ggml org Ggml Backend Plugin Loading
- Principle:Triton inference server Server Ensemble Pipeline Design
Implementations
- Implementation:Apache Paimon RoaringBitmap
- Implementation:Webdriverio Webdriverio Browser Runner Render
- Implementation:Ray project Ray Ray Init Cross Language
- Implementation:Sktime Pytorch forecasting Show Versions
- Implementation:ArroyoSystems Arroyo Delta Connector
- Implementation:FlagOpen FlagEmbedding Reinforced IR Multi GPU
- Implementation:Cohere ai Cohere python ChatCitation Model
- Implementation:FlagOpen FlagEmbedding LLM Reranker Instruction Data
- Implementation:Intel Ipex llm IpexLLM From Model Id
- Implementation:Openai Openai node Speech Resource
Heuristics
- Heuristic:TobikoData Sqlmesh Snapshot TTL Defaults
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:Huggingface Open r1 Code Execution Timeout Strategy
- Heuristic:ContextualAI HALOs Humanline Clamping
- Heuristic:Wandb Weave Batch Processing Tuning
- Heuristic:Microsoft Playwright Test Stability Practices
- Heuristic:DevExpress Testcafe Browser Connection Timeouts
- Heuristic:Apache Dolphinscheduler Netty Thread Sizing
- Heuristic:Zai org CogVideo Memory Optimization Strategies
- Heuristic:AnswerDotAI RAGatouille FAISS Vs PyTorch KMeans Indexing
Environments
- Environment:Onnx Onnx Cpp Build Environment
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Arize ai Phoenix LLM Provider SDKs
- Environment:Hiyouga LLaMA Factory Quantization Dependencies
- Environment:ThreeSR Awesome Inference Time Scaling GitHub Account Environment
- Environment:Eventual Inc Daft AI Provider Dependencies
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment
- Environment:Openai Openai node OpenAI API Credentials
- Environment:LLMBook zh LLMBook zh github io VLLM Inference Environment
- Environment:Ollama Ollama GPU Runtime