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:Mlc ai Mlc llm Model Compilation
- Workflow:PrefectHQ Prefect API Sourced ETL
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Open compass VLMEvalKit API Model Evaluation
- Workflow:Triton inference server Server LLM Deployment With TRT LLM
- Workflow:Microsoft Autogen Swarm Agent Handoff
- Workflow:Unstructured IO Unstructured Performance Profiling
- Workflow:Spotify Luigi Database Ingestion Pipeline
- Workflow:ARISE Initiative Robosuite Human Demonstration Collection
- Workflow:Ray project Ray Actor Lifecycle Management
Principles
- Principle:DataExpert io Data engineer handbook Database Seeding
- Principle:Lm sys FastChat Chat Data Cleaning
- Principle:Mlc ai Web llm Tool Call Extraction
- Principle:Zai org CogVideo Caption Model Loading
- Principle:Ucbepic Docetl Pipeline Export
- Principle:Huggingface Trl SFT Training Execution
- Principle:ClickHouse ClickHouse Code Coverage Collection
- Principle:Zai org CogVideo LLM Image Video Pipeline
- Principle:Pola rs Polars Data Output Validation
- Principle:Langfuse Langfuse Export Job Creation
Implementations
- Implementation:Interpretml Interpret BoosterShell Hpp
- Implementation:Getgauge Taiko Goto
- Implementation:Ray project Ray BaseActorCreator
- Implementation:Cleanlab Cleanlab CleanLearning Fit
- Implementation:Langgenius Dify Docker Compose Up
- Implementation:Pyro ppl Pyro FoldedDistribution
- Implementation:Facebookresearch Habitat lab TensorDict
- Implementation:Microsoft Playwright DevtoolsController
- Implementation:Apache Paimon PredicateBuilder Filtering
- Implementation:ArroyoSystems Arroyo Polling Http Operator
Heuristics
- Heuristic:Kserve Kserve VLLM GPU Memory Utilization
- Heuristic:MarketSquare Robotframework browser MacOS Sonoma Startup Delay
- Heuristic:Apache Spark Warning Deprecated DStream Streaming
- Heuristic:NVIDIA NeMo Aligner PPO NCCL Algorithm Setting
- Heuristic:Apache Beam Executor Shutdown Ordering
- Heuristic:Interpretml Interpret Memory Budget Heuristic
- Heuristic:Protectai Llm guard ONNX Runtime Optimization
- Heuristic:Openai CLIP CLIP Normalization Constants
- Heuristic:Facebookresearch Habitat lab Resume State Config Override
- Heuristic:Deepset ai Haystack BM25 Score Scaling
Environments
- Environment:Truera Trulens LangChain LangGraph Environment
- Environment:Bigscience workshop Petals CUDA Server
- Environment:Huggingface Datasets Image Dependencies
- Environment:BerriAI Litellm Observability Stack
- Environment:DataTalksClub Data engineering zoomcamp PySpark Batch Environment
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:ChenghaoMou Text dedup Suffix Array External Tools
- Environment:Intel Ipex llm NPU Environment
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment