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:FlowiseAI Flowise Agentflow V2 Creation
- Workflow:Dotnet Machinelearning Time Series Forecasting
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:ContextualAI HALOs Model Evaluation
- Workflow:OpenHands OpenHands GitHub Webhook Event Processing
- Workflow:AUTOMATIC1111 Stable diffusion webui Textual inversion training
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:Duckdb Duckdb Benchmark Execution
- Workflow:Huggingface Optimum GPTQ Quantization
- Workflow:Neuml Txtai Semantic Search Pipeline
Principles
- Principle:Triton inference server Server Command Line Parsing
- Principle:ClickHouse ClickHouse Server Startup For Testing
- Principle:Mit han lab Llm awq LLaVA Multimodal Architecture
- Principle:Deepspeedai DeepSpeed Reward Model Training
- Principle:OpenGVLab InternVL DDP Gradient Compression
- Principle:Microsoft LoRA Beam Search Generation
- Principle:Gretelai Gretel synthetics Batch Model Training
- Principle:Facebookresearch Habitat lab Low level Skill Training
- Principle:Iterative Dvc Data Structure Utilities
- Principle:Marker Inc Korea AutoRAG Schema Construction
Implementations
- Implementation:Puppeteer Puppeteer Chrome Browser Data
- Implementation:Huggingface Datatrove HuggingFaceDatasetWriter
- Implementation:Avhz RustQuant HoLee
- Implementation:Lance format Lance ConstantEncoding
- Implementation:Helicone Helicone CostOfPrompt
- Implementation:Open compass VLMEvalKit EMMADataset
- Implementation:ArroyoSystems Arroyo Pipeline Graph
- Implementation:Marker Inc Korea AutoRAG ApiRunner Run Api Server
- Implementation:Microsoft Onnxruntime ESLintConfig
- Implementation:Apache Paimon DLFAuthProviderFactory
Heuristics
- Heuristic:Kubeflow Pipelines Component URL Commit SHA Pinning
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:Scikit learn Scikit learn Convergence Warning Handling
- Heuristic:Google research Deduplicate text datasets Ulimit File Descriptors For Merge
- Heuristic:Huggingface Trl DeepSpeed ZeRO3 Generation Tradeoff
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:Pola rs Polars Lazy Over Eager Preference
- Heuristic:Spotify Luigi Atomic File Writes
- Heuristic:ContextualAI HALOs Reference Logprob Caching
- Heuristic:Zai org CogVideo Scheduler and Guidance Selection
Environments
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:Deepspeedai DeepSpeed XPU Environment
- Environment:Duckdb Duckdb Code Generation Tools
- Environment:Openai Openai python Realtime WebSocket
- Environment:Apache Spark Python Environment
- Environment:Alibaba ROLL vLLM Inference Environment
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Volcengine Verl vLLM Rollout Environment
- Environment:Hpcaitech ColossalAI ColossalQA RAG Environment
- Environment:Openai Openai node Node 20 Runtime