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:Ggml org Llama cpp Text Generation
- Workflow:Interpretml Interpret Blackbox Model Explanation
- Workflow:FlowiseAI Flowise Chatbot Deployment
- Workflow:Infiniflow Ragflow Docker Deployment
- Workflow:Unslothai Unsloth Model Export And Deployment
- Workflow:PrefectHQ Prefect Per Worker Task Concurrency
- Workflow:Wandb Weave Prompt Management
- Workflow:Webdriverio Webdriverio Component Testing
- Workflow:ContextualAI HALOs Model Evaluation
- Workflow:Microsoft Playwright API testing
Principles
- Principle:Langfuse Langfuse Experiment Run Creation
- Principle:Sktime Pytorch forecasting Point Loss Functions
- Principle:Zai org CogVideo Laplacian Pyramid Loss
- Principle:Online ml River Pipeline Composition
- Principle:FMInference FlexLLMGen Execution Environment Initialization
- Principle:Huggingface Open r1 Chat Template Formatting
- Principle:Confident ai Deepeval Framework Instrumentation
- Principle:Interpretml Interpret Score Tensor Harmonization
- Principle:Open compass VLMEvalKit Video Inference Orchestration
- Principle:CARLA simulator Carla Simulation Replay
Implementations
- Implementation:Pyro ppl Pyro Autoname Mixture
- Implementation:Openai Openai python Shared All Models
- Implementation:Open compass VLMEvalKit Video MMLU CAP
- Implementation:Apache Flink SourceReaderOptions
- Implementation:ArroyoSystems Arroyo Var Str
- Implementation:Sdv dev SDV CTGANSynthesizer Init
- Implementation:Google deepmind Mujoco MJX Warp Smooth
- Implementation:Haotian liu LLaVA Model Generate Multimodal
- Implementation:Apache Druid RollupAnalysisPane
- Implementation:Ollama Ollama Tokenizer SentencePiece
Heuristics
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
- Heuristic:Avdvg InjectGuard Module Level Initialization
- Heuristic:ThreeSR Awesome Inference Time Scaling API Rate Limiting Tip
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:Eventual Inc Daft Execution Config Tuning
- Heuristic:NVIDIA DALI Distributed Sharding Strategy
- Heuristic:Unstructured IO Unstructured Multi Python Matrix
- Heuristic:ArroyoSystems Arroyo Worker Heartbeat Timeout
- Heuristic:AnswerDotAI RAGatouille Collection Size Index Tuning
- Heuristic:Dotnet Machinelearning FastTree Default Hyperparameters
Environments
- Environment:MarketSquare Robotframework browser Python Runtime
- Environment:Cleanlab Cleanlab Python Core Environment
- Environment:Vllm project Vllm AArch64 CPU
- Environment:Deepset ai Haystack HuggingFace Model Environment
- Environment:CrewAIInc CrewAI LLM Provider Credentials
- Environment:Apache Flink Hadoop Compatibility Environment
- Environment:Pola rs Polars GPU Execution Environment
- Environment:Microsoft DeepSpeedExamples VisualChat Training Environment
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:Interpretml Interpret Visualization Environment