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:Tencent Ncnn Vulkan GPU Accelerated Inference
- Workflow:Anthropics Anthropic sdk python Extended Thinking Reasoning
- Workflow:Confident ai Deepeval End to End LLM Evaluation
- Workflow:Langchain ai Langchain Chat Model Invocation
- Workflow:Google deepmind Dm control Composer Environment Building
- Workflow:Spotify Luigi Hadoop MapReduce Pipeline
- Workflow:Deepseek ai Janus Rectified Flow Image Generation
- Workflow:Farama Foundation Gymnasium Vectorized Environment Training
- Workflow:Norrrrrrr lyn WAInjectBench Text Prompt Injection Detection
- Workflow:Deepset ai Haystack RAG Pipeline
Principles
- Principle:SeldonIO Seldon core Experiment Configuration
- Principle:Apache Dolphinscheduler RPC Client Proxy Pattern
- Principle:Sdv dev SDV Diagnostic Reporting
- Principle:Ucbepic Docetl Output Management
- Principle:PeterL1n BackgroundMattingV2 ONNX export
- Principle:Liu00222 Open Prompt Injection Model Creation
- Principle:Run llama Llama index Embedding Finetune Configuration
- Principle:Huggingface Diffusers Diffusion Training Loop
- Principle:Evidentlyai Evidently Snapshot Storage
- Principle:Apache Paimon FAISS Index Configuration
Implementations
- Implementation:Vllm project Vllm Benchmark Serving Structured Output
- Implementation:Mlc ai Web llm Get Message Model Routing
- Implementation:FMInference FlexLLMGen HELM Metric Evaluate
- Implementation:Cohere ai Cohere python BedrockClientV2 Init
- Implementation:Microsoft LoRA Legacy Seq2Seq Utils
- Implementation:CARLA simulator Carla RPC Server
- Implementation:OpenGVLab InternVL InternLM2TokenizerFast
- Implementation:Online ml River Ensemble VotingClassifier
- Implementation:Ggml org Llama cpp Graph Header
- Implementation:Webdriverio Webdriverio ModuleHookTracker Class
Heuristics
- Heuristic:Microsoft Playwright Timeout Configuration Tips
- Heuristic:Alibaba MNN NC4HW4 Data Layout
- Heuristic:Rapidsai Cuml Dask Data Partitioning
- Heuristic:Interpretml Interpret Memory Budget Heuristic
- Heuristic:Astronomer Astronomer cosmos Cache Strategy Optimization
- Heuristic:HKUDS AI Trader Sortino Ratio Capping
- Heuristic:Apache Paimon File Sizing and Split Planning
- Heuristic:Apache Airflow Variable Access Pattern
- Heuristic:Datajuicer Data juicer Operator Fusion Rules
- Heuristic:Huggingface Datatrove FineWeb Filter Pipeline Order
Environments
- Environment:Scikit learn contrib Imbalanced learn Python Scikit learn
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:Vllm project Vllm AArch64 CPU
- Environment:ArroyoSystems Arroyo PostgreSQL Database
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:Google deepmind Dm control EGL Headless Rendering
- Environment:Alibaba MNN CPU Build Environment
- Environment:Microsoft DeepSpeedExamples RLHF Training Environment
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:Infiniflow Ragflow Docker Infrastructure