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:Langchain ai Langchain Release Process
- Workflow:Confident ai Deepeval Component Level LLM Evaluation
- Workflow:Apache Spark Building and Testing
- Workflow:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:Ollama Ollama Model Pull And Run
- Workflow:Microsoft Agent framework Declarative Agent Definition
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:Microsoft Autogen Studio Team Deployment
Principles
- Principle:BerriAI Litellm Fine Tuned Model Usage
- Principle:Run llama Llama index Evaluator Configuration
- Principle:Sktime Pytorch forecasting NBeats Model Instantiation
- Principle:Roboflow Rf detr COCO Evaluation
- Principle:Obss Sahi Model Initialization
- Principle:Eventual Inc Daft Parquet Writing
- Principle:Microsoft Playwright Configure API Request Context
- Principle:Huggingface Optimum CLI Command Framework
- Principle:Liu00222 Open Prompt Injection Model Query Interface
- Principle:TA Lib Ta lib python Price Data Preparation
Implementations
- Implementation:TobikoData Sqlmesh LineageLayoutBase
- Implementation:InternLM Lmdeploy GemmUniversalSm90V5
- Implementation:Spotify Luigi Sphinx Doc Configuration
- Implementation:Ollama Ollama Convert Olmo
- Implementation:Deepspeedai DeepSpeed AutoModel For Inference
- Implementation:Openai Openai python Chat Completion Message Param
- Implementation:MarketSquare Robotframework browser PluginParser Parse Plugins
- Implementation:Apache Druid FlexibleQueryInput
- Implementation:Intel Ipex llm NPU Multimodal MiniCPM
- Implementation:Facebookresearch Audiocraft Hydra YAML Composition
Heuristics
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Allenai Open instruct GPU Memory Utilization
- Heuristic:Fede1024 Rust rdkafka Multi Version Dependency Hazard
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
- Heuristic:LaurentMazare Tch rs MPS Weight Loading Workaround
- Heuristic:Ucbepic Docetl Validation Retry Strategy
- Heuristic:Onnx Onnx Opset Version Selection
- Heuristic:Deepspeedai DeepSpeed FP16 Convergence Tips
- Heuristic:Infiniflow Ragflow Embedding Batch Size Constraint
- Heuristic:Promptfoo Promptfoo Adaptive Concurrency Tuning
Environments
- Environment:Farama Foundation Gymnasium MuJoCo Physics Backend
- Environment:Vllm project Vllm CUDA
- Environment:Volcengine Verl Megatron Core Environment
- Environment:Protectai Modelscan H5py Optional
- Environment:Alibaba ROLL Diffusion Video Environment
- Environment:Unstructured IO Unstructured Libmagic
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:SqueezeAILab ETS Evaluation Python Stack
- Environment:PrefectHQ Prefect AI Integration Credentials
- Environment:Vllm project Vllm AMD ROCm