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:BerriAI Litellm Router Load Balancing
- Workflow:Cohere ai Cohere python Chat Completion
- Workflow:Mlc ai Mlc llm Mobile Deployment
- Workflow:Allenai Open instruct Reward Model Training
- Workflow:Bentoml BentoML BentoCloud Deployment
- Workflow:Run llama Llama index RAG Query Pipeline
- Workflow:Ray project Ray Serve Deployment
- Workflow:Microsoft Playwright API testing
- Workflow:Microsoft Autogen Multi Agent Conversation
- Workflow:Princeton nlp Tree of thought llm ToT BFS experiment
Principles
- Principle:Apache Spark Test Orchestration
- Principle:Ollama Ollama Modelfile Parsing
- Principle:Sktime Pytorch forecasting Time Series Dataset Construction
- Principle:Cleanlab Cleanlab Active Learning Prioritization
- Principle:Haotian liu LLaVA Multimodal Response Generation
- Principle:Bentoml BentoML Cloud Deployment Creation
- Principle:TobikoData Sqlmesh Model Definition
- Principle:Apache Paimon Batch Data Writing
- Principle:Openai Whisper Audio Loading
- Principle:Langchain ai Langgraph Graph Configuration Management
Implementations
- Implementation:Guardrails ai Guardrails Guard For Pydantic
- Implementation:NVIDIA NeMo Curator RapidsMPFShuffler
- Implementation:Truera Trulens Leaderboard Tab
- Implementation:Wandb Weave Run Setup In Codex
- Implementation:LMCache LMCache Logging
- Implementation:NVIDIA NeMo Curator Wikipedia Extractor
- Implementation:Ucbepic Docetl FastShouldOptimize
- Implementation:Ggml org Llama cpp Common Speculative Draft
- Implementation:SeleniumHQ Selenium Closure Object
- Implementation:Arize ai Phoenix ToolResponseHandlingEvaluator
Heuristics
- Heuristic:AnswerDotAI RAGatouille Auto Batch Size For Long Documents
- Heuristic:Apache Hudi Data Skipping Limitations
- Heuristic:NVIDIA NeMo Curator Semantic Dedup Cluster Sizing
- Heuristic:Bentoml BentoML Warning Deprecated Server Module
- Heuristic:Neuml Txtai Memory Streaming Optimization
- Heuristic:MaterializeInc Materialize CI Retry Strategies
- Heuristic:Sdv dev SDV Version Compatibility
- Heuristic:Getgauge Taiko Network Interception Gotchas
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
Environments
- Environment:LaurentMazare Tch rs Libtorch Build Environment
- Environment:Ray project Ray Docker GPU Environment
- Environment:AUTOMATIC1111 Stable diffusion webui Python And PyTorch Runtime
- Environment:Openclaw Openclaw Docker Deployment Environment
- Environment:Intel Ipex llm XPU Inference Environment
- Environment:Spotify Luigi Python Runtime
- Environment:Microsoft DeepSpeedExamples RLHF Training Environment
- Environment:Microsoft BIPIA OpenAI API Environment
- Environment:Online ml River Build Toolchain
- Environment:Vespa engine Vespa FNET Transport Config