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:Princeton nlp Tree of thought llm ToT BFS experiment
- Workflow:Togethercomputer Together python Fine Tuning
- Workflow:Googleapis Python genai Multi Turn Chat
- Workflow:Cleanlab Cleanlab Token Classification Label Quality
- Workflow:Openai Openai node Structured Output Parsing
- Workflow:Norrrrrrr lyn WAInjectBench LLaVA Finetuning
- Workflow:Triton inference server Server Quickstart Model Deployment
- Workflow:Obss Sahi COCO Evaluation
- Workflow:Huggingface Diffusers Model Quantization
- Workflow:Unslothai Unsloth GRPO Reinforcement Learning
Principles
- Principle:Microsoft Onnxruntime Distributed Data Loading
- Principle:Dotnet Machinelearning Text Featurization
- Principle:NVIDIA TransformerEngine Fused LayerNorm Linear
- Principle:Unslothai Unsloth MoE Grouped GEMM
- Principle:Helicone Helicone Environment Configuration
- Principle:Infiniflow Ragflow Embedding Generation
- Principle:MaterializeInc Materialize Composition Execution
- Principle:Microsoft Semantic kernel Vector Store Data Model
- Principle:EvolvingLMMs Lab Lmms eval PassAtK Evaluation
- Principle:Open compass VLMEvalKit Model Validation
Implementations
- Implementation:Sdv dev SDV Run Diagnostic
- Implementation:Googleapis Python genai LocalTokenizer
- Implementation:Apache Paimon TableUpdateByRowId
- Implementation:Datahub project Datahub Container Key Guid Generator
- Implementation:Fede1024 Rust rdkafka MockCluster Bootstrap Servers
- Implementation:MarketSquare Robotframework browser Selector Finder
- Implementation:Mlflow Mlflow Pyproject Configuration
- Implementation:Helicone Helicone GetMapperType
- Implementation:Online ml River Tree Splitter NominalReg
- Implementation:FlowiseAI Flowise DocStoreInputHandler
Heuristics
- Heuristic:Langchain ai Langchain Pydantic V2 Configuration Tips
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:Axolotl ai cloud Axolotl Attention Mechanism Selection
- Heuristic:Speechbrain Speechbrain Nonfinite Loss Handling
- Heuristic:Onnx Onnx Opset Version Selection
- Heuristic:Sktime Pytorch forecasting Learning Rate Scheduling
- Heuristic:Dotnet Machinelearning Sparsity Threshold Optimization
- Heuristic:Obss Sahi Match Threshold Tuning
- Heuristic:OpenBMB UltraFeedback Position Bias Mitigation
- Heuristic:SqueezeAILab ETS Max Depth And Token Guards
Environments
- Environment:ArroyoSystems Arroyo Rust Runtime
- Environment:TobikoData Sqlmesh Snowflake Connection
- Environment:Mlflow Mlflow MLflow Server Environment
- Environment:Intel Ipex llm XPU Inference Environment
- Environment:Obss Sahi Python Pycocotools
- Environment:OpenRLHF OpenRLHF DeepSpeed Environment
- Environment:Eric mitchell Direct preference optimization Python Dependencies
- Environment:Nautechsystems Nautilus trader Python Cython Rust Runtime
- Environment:EvolvingLMMs Lab Lmms eval GPU Compute Environment
- Environment:Lm sys FastChat SFT Training Environment