Main Page
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:Spcl Graph of thoughts GoT Document Merging Pipeline
- Workflow:Snorkel team Snorkel Slice Aware Training
- Workflow:Sdv dev SDV Data quality evaluation
- Workflow:Tensorflow Serving Batched Inference Pipeline
- Workflow:Openclaw Openclaw Multi Agent Routing
- Workflow:Recommenders team Recommenders SAR Collaborative Filtering
- Workflow:Google research Deduplicate text datasets Suffix array querying
- Workflow:Interpretml Interpret EBM Model Merging
- Workflow:Apache Dolphinscheduler Datasource Connection Management
- Workflow:Heibaiying BigData Notes Hive Data Warehouse Operations
Principles
- Principle:Guardrails ai Guardrails Remote Guard Connection
- Principle:Kserve Kserve Model Promotion Rollback
- Principle:Anthropics Anthropic sdk python Parsed Output Access
- Principle:Mlc ai Mlc llm Engine Configuration
- Principle:Confident ai Deepeval API Key Management
- Principle:CrewAIInc CrewAI Embedding Configuration
- Principle:Ollama Ollama HardwareDiscovery
- Principle:Treeverse LakeFS Integration Test Utilities
- Principle:Vespa engine Vespa Indexing Error Handling
- Principle:DataTalksClub Data engineering zoomcamp Schema Normalization
Implementations
- Implementation:Infiniflow Ragflow PackageLock Dependencies
- Implementation:Ollama Ollama ML Backend
- Implementation:Ray project Ray Buildkite Aarch64 Pipeline
- Implementation:PrefectHQ Prefect Worker CLI Commands
- Implementation:Vibrantlabsai Ragas Text2SQL Validate Dataset
- Implementation:Hpcaitech ColossalAI Zero Bubble Consumer
- Implementation:Pola rs Polars DataFrame Group By
- Implementation:Eric mitchell Direct preference optimization Get Batch Logps
- Implementation:FlowiseAI Flowise ChatInputHistory
- Implementation:Google deepmind Dm control Viewer Util
Heuristics
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:Facebookresearch Habitat lab Warning Deprecated Legacy UI System
- Heuristic:Openclaw Openclaw Retry With Exponential Backoff
- Heuristic:SeleniumHQ Selenium Warning Deprecated Proxy FTP Methods
- Heuristic:LaurentMazare Tch rs Device Fallback Pattern
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
- Heuristic:Openai Openai node RunTools Loop Limit
- Heuristic:Openai Openai python Warning Deprecated Legacy Response
- Heuristic:NVIDIA DALI Memory Pool Tuning
- Heuristic:Bitsandbytes foundation Bitsandbytes Compressed Statistics Double Quantization
Environments
- Environment:Getgauge Taiko Node Runtime
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:Vllm project Vllm AMD ROCm
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Openclaw Openclaw Node 22 Runtime
- Environment:Roboflow Rf detr Python GPU Environment
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:Mlc ai Mlc llm Metal macOS iOS Environment
- Environment:Datahub project Datahub Frontend Build
- Environment:Huggingface Datasets Image Dependencies