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:FlagOpen FlagEmbedding Reranker Finetuning
- Workflow:Mage ai Mage ai API Source Extraction
- Workflow:Fastai Fastbook Tabular Modeling
- Workflow:Deepset ai Haystack Document Preprocessing Pipeline
- Workflow:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:MarketSquare Robotframework browser API Testing via Browser
- Workflow:Puppeteer Puppeteer Browser Installation And Management
- Workflow:Volcengine Verl Data Preprocessing For RL
- Workflow:Liu00222 Open Prompt Injection Detection Localization Defense
- Workflow:Allenai Open instruct SFT Finetuning
Principles
- Principle:OpenGVLab InternVL Flash Attention Optimization
- Principle:Microsoft Playwright Extract Data with Agent
- Principle:Cypress io Cypress Contribution Workflow
- Principle:Eventual Inc Daft Session SQL Execution
- Principle:PacktPublishing LLM Engineers Handbook LoRA Adapter Injection
- Principle:Huggingface Datatrove Local Pipeline Execution
- Principle:Pytorch Serve Non PyTorch Model Serving
- Principle:DevExpress Testcafe Runner Creation
- Principle:Huggingface Open r1 Supervised Fine Tuning
- Principle:Neuml Txtai Speech Synthesis
Implementations
- Implementation:Online ml River FeatureExtraction PolynomialExtender
- Implementation:Risingwavelabs Risingwave SourceTypeE
- Implementation:Cleanlab Cleanlab Coteaching Train
- Implementation:ArroyoSystems Arroyo Impulse Operator
- Implementation:Ollama Ollama MLXRunner Array
- Implementation:Microsoft Playwright WkExecutionContext
- Implementation:Onnx Onnx Helper Make Tensor Value Info
- Implementation:Openai Openai agents python Runner Resume Pattern
- Implementation:CrewAIInc CrewAI GitHub Search Tool
- Implementation:Evidentlyai Evidently Legacy Non Letter Char Feature
Heuristics
- Heuristic:Heibaiying BigData Notes Hive ORC Parquet Storage Tip
- Heuristic:DevExpress Testcafe Concurrency Factor Limit
- Heuristic:Nautechsystems Nautilus trader Inflight Order Check Threshold
- Heuristic:Ollama Ollama Multimodal Parallel Restriction
- Heuristic:Princeton nlp Tree of thought llm Value Caching
- Heuristic:Kornia Kornia Lazy Loading Optional Deps
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
- Heuristic:Huggingface Datatrove Gopher Quality Thresholds
- Heuristic:Tensorflow Tfjs WASM Cross Origin Isolation
- Heuristic:Lm sys FastChat GPU Memory Allocation Strategy
Environments
- Environment:NVIDIA NeMo Curator Video Codec Stack
- Environment:Neuml Txtai Python Core Environment
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:Roboflow Rf detr ONNX Export Environment
- Environment:Truera Trulens OpenAI Provider Environment
- Environment:Vllm project Vllm AMD ROCm
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Volcengine Verl CUDA GPU Environment
- Environment:Sgl project Sglang CUDA
- Environment:Pola rs Polars Rust Build Environment