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:Guardrails ai Guardrails Streaming Validation
- Workflow:Shiyu coder Kronos Qlib Finetuning
- Workflow:Huggingface Open r1 Reasoning Data Generation
- Workflow:Apache Hudi Flink Schema Evolution
- Workflow:Marker Inc Korea AutoRAG RAG Pipeline Optimization
- Workflow:Alibaba MNN Model Conversion Pipeline
- Workflow:Zai org CogVideo Diffusers Text to Video Inference
- Workflow:Huggingface Peft LoRA Causal LM Finetuning
- Workflow:Rapidsai Cuml Time Series Forecasting
- Workflow:Mbzuai oryx Awesome LLM Post training Awesome List Curation
Principles
- Principle:Ollama Ollama Model Alias Resolution
- Principle:Confident ai Deepeval Retriever Span Enrichment
- Principle:AUTOMATIC1111 Stable diffusion webui VAE decoding
- Principle:Speechbrain Speechbrain Sound Classification Training
- Principle:Huggingface Datasets Lance Dataset Building
- Principle:Microsoft Onnxruntime Nodejs Session Creation
- Principle:Langfuse Langfuse OTel Input Output Extraction
- Principle:Huggingface Datatrove FineWeb Quality Heuristics
- Principle:FMInference FlexLLMGen Execution Environment Initialization
- Principle:Webdriverio Webdriverio TypeScript Type Safety
Implementations
- Implementation:ArroyoSystems Arroyo Jobs Api
- Implementation:DevExpress Testcafe ClientFunction TypeDefs
- Implementation:Volcengine Verl Dataset To Parquet
- Implementation:Teamcapybara Capybara Queries BaseQuery
- Implementation:CrewAIInc CrewAI Knowledge Source Classes
- Implementation:Langgenius Dify InputVar Types
- Implementation:MaterializeInc Materialize CLI Workload Capture
- Implementation:Volcengine Verl Compute Value Loss
- Implementation:Haosulab ManiSkill KitchenObjectUtils
- Implementation:OpenHands OpenHands OrgService Validate Name Uniqueness
Heuristics
- Heuristic:Princeton nlp Tree of thought llm API Request Batching
- Heuristic:LLMBook zh LLMBook zh github io BF16 Mixed Precision Default
- Heuristic:MarketSquare Robotframework browser Shared Node Process For Parallel
- Heuristic:Datahub project Datahub Venv Copies Mode
- Heuristic:Mlflow Mlflow Batch Logging Size Limits
- Heuristic:Farama Foundation Gymnasium Sync Vs Async VectorEnv Selection
- Heuristic:Intel Ipex llm Use Cache Training Vs Inference
- Heuristic:Neuml Txtai LLM Context Window Fallback
- Heuristic:Open compass VLMEvalKit Judge Model Selection By Dataset
- Heuristic:Langchain ai Langgraph Retry Policy Configuration
Environments
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:CARLA simulator Carla Python API Runtime
- Environment:OpenBMB UltraFeedback HuggingFace Hub Environment
- Environment:Evidentlyai Evidently LLM Evaluation Environment
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA
- Environment:InternLM Lmdeploy Build From Source
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Protectai Llm guard Python Runtime Dependencies
- Environment:Datahub project Datahub Docker Quickstart Environment
- Environment:Evidentlyai Evidently Node Frontend Environment