Main Page
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:Huggingface Datasets Format Conversion
- Workflow:Infiniflow Ragflow Knowledge Base Document Ingestion
- Workflow:InternLM Lmdeploy VLM Inference Pipeline
- Workflow:Openclaw Openclaw Gateway Operations And Diagnostics
- Workflow:Sktime Pytorch forecasting TFT Demand Forecasting
- Workflow:Lakeraai Pint benchmark Hugging Face Model Evaluation
- Workflow:Openai Openai agents python Basic Agent Execution
- Workflow:Risingwavelabs Risingwave Iceberg Lakehouse Ingestion
- Workflow:NVIDIA NeMo Curator Video Curation Pipeline
- Workflow:Princeton nlp SimPO SimPO Training
Principles
- Principle:Promptfoo Promptfoo Provider Interface
- Principle:Hiyouga LLaMA Factory Muon Optimization
- Principle:FlagOpen FlagEmbedding Evaluation Model Loading
- Principle:Farama Foundation Gymnasium Vector Episode Statistics
- Principle:LLMBook zh LLMBook zh github io Reward Modeling
- Principle:Apache Hudi Clustering Commit
- Principle:Farama Foundation Gymnasium Episode Time Limiting
- Principle:Langgenius Dify BrandingConfiguration
- Principle:Isaac sim IsaacGymEnvs Randomization State Initialization
- Principle:Sdv dev SDV Range Constraint
Implementations
- Implementation:Microsoft Onnxruntime TrainingRunner Initialize
- Implementation:Lm sys FastChat Clean Battle Data
- Implementation:Apache Druid CompactionHistoryDialog
- Implementation:Ray project Ray MessagePackSerializer Encode
- Implementation:DevExpress Testcafe TestController TypeDefs
- Implementation:Deepspeedai DeepSpeed Inference Cublas Wrappers
- Implementation:Langgenius Dify URL Validation
- Implementation:Risingwavelabs Risingwave PostgresSchema
- Implementation:Microsoft Onnxruntime TorchCustomFunctionKernelBase
- Implementation:BerriAI Litellm Completion With Fine Tuned Model
Heuristics
- Heuristic:Mlc ai Mlc llm Optimization Level Selection
- Heuristic:Apache Spark Hardware Provisioning Tips
- Heuristic:Helicone Helicone Rate Limiting Fail Open
- Heuristic:TobikoData Sqlmesh Execution Time Caching
- Heuristic:Avhz RustQuant Interpolation Method Selection
- Heuristic:Openai Openai python Timeout Connection Defaults
- Heuristic:Mlc ai Web llm Service Worker Keep Alive
- Heuristic:Openai Whisper SDPA Disabling For Attention Extraction
- Heuristic:Neuml Txtai Batch Size Defaults
- Heuristic:SeleniumHQ Selenium Bazel Hermetic Build Requirement
Environments
- Environment:Anthropics Anthropic sdk python Python SDK Core Environment
- Environment:Langgenius Dify Docker Compose Environment
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:MarketSquare Robotframework browser Docker Container
- Environment:NVIDIA DALI CMake Build Environment
- Environment:Alibaba ROLL Diffusion Video Environment
- Environment:Turboderp org Exllamav2 Build Toolchain
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:Apache Beam Portable Runner Environment
- Environment:Intel Ipex llm CPU Finetuning Environment