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:Nightwatchjs Nightwatch Component Testing
- Workflow:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Dotnet Machinelearning Text Classification
- Workflow:Cohere ai Cohere python Text Embedding
- Workflow:Webdriverio Webdriverio Custom Plugin Development
- Workflow:Zai org CogVideo SAT Finetuning
- Workflow:Ollama Ollama OpenAI API Compatibility
- Workflow:Teamcapybara Capybara Custom Selector Definition
- Workflow:NVIDIA TransformerEngine Comm GEMM Overlap Training
- Workflow:Alibaba ROLL Reward Flow Diffusion Pipeline
Principles
- Principle:Vespa engine Vespa Artifact Signing and Publishing
- Principle:Allenai Open instruct Reward Verification
- Principle:Eric mitchell Direct preference optimization Hydra Configuration
- Principle:NVIDIA DALI Image Decoding
- Principle:Astronomer Astronomer cosmos Dbt Documentation Generation
- Principle:Ray project Ray Cross Language Deserialization
- Principle:AUTOMATIC1111 Stable diffusion webui Sampling Architecture
- Principle:Marker Inc Korea AutoRAG Best Config Extraction
- Principle:Microsoft Agent framework Chat Client Configuration
- Principle:Tensorflow Serving Multi Version Export
Implementations
- Implementation:Run llama Llama index IngestionPipeline Init
- Implementation:SqueezeAILab ETS Tree Expand
- Implementation:PacktPublishing LLM Engineers Handbook TrainTestSplit To Huggingface
- Implementation:Huggingface Datatrove MimeTypeFilter
- Implementation:Kornia Kornia BoxMOT Tracker
- Implementation:Fastai Fastbook Feature Importances
- Implementation:OpenGVLab InternVL LLaVA Controller
- Implementation:Speechbrain Speechbrain Prepare Common Voice
- Implementation:Langchain ai Langgraph Langgraph Build Command
- Implementation:Arize ai Phoenix HallucinationEvaluator
Heuristics
- Heuristic:OpenGVLab InternVL Dynamic Resolution Tiling
- Heuristic:Infiniflow Ragflow Reranking Weight Tuning
- Heuristic:Roboflow Rf detr Layer Wise LR Decay
- Heuristic:Huggingface Open r1 Distributed Training Configuration
- Heuristic:Onnx Onnx Big Endian Byte Order Handling
- Heuristic:Dagster io Dagster Retry Strategy Configuration
- Heuristic:Mlflow Mlflow Batch Logging Size Limits
- Heuristic:ARISE Initiative Robomimic HDF5 Cache Mode Selection
- Heuristic:NVIDIA NeMo Aligner PPO Critic Warmup Tip
- Heuristic:Mage ai Mage ai Sorted Data Bookmark Strategy
Environments
- Environment:Openai Openai node WebSocket Dependency
- Environment:Datajuicer Data juicer Ray Cluster Environment
- Environment:Mlc ai Mlc llm TVM Runtime Environment
- Environment:Microsoft Agent framework Python 3 10 Runtime
- Environment:Hpcaitech ColossalAI ColossalQA RAG Environment
- Environment:Sgl project Sglang OpenAI
- Environment:Treeverse LakeFS S3 Gateway Test Environment
- Environment:Protectai Llm guard ONNX Runtime Acceleration
- Environment:MarketSquare Robotframework browser CI GitHub Actions
- Environment:Dotnet Machinelearning TorchSharp Environment