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:Apache Paimon Vector Similarity Search
- Workflow:Pyro ppl Pyro Discrete Enumeration
- Workflow:DataTalksClub Data engineering zoomcamp Docker PostgreSQL Data Ingestion
- Workflow:MaterializeInc Materialize Release Process
- Workflow:Intel Ipex llm RAG With LangChain
- Workflow:Ollama Ollama Model Pull And Run
- Workflow:Hpcaitech ColossalAI RAG Application
- Workflow:Heibaiying BigData Notes Storm Topology Development
- Workflow:Shiyu coder Kronos Single Series Prediction
- Workflow:Openai Evals Creating a model graded eval
Principles
- Principle:Huggingface Datatrove NGram Decontamination
- Principle:Pyro ppl Pyro Gradient Estimation
- Principle:Onnx Onnx Opset Version Conversion
- Principle:Promptfoo Promptfoo Test Suite Construction
- Principle:Openai Openai python Chat Message Construction
- Principle:DistrictDataLabs Yellowbrick Missing Data Visualization
- Principle:Ollama Ollama ModelArchitecture
- Principle:Openai Openai agents python Execution Resumption
- Principle:Norrrrrrr lyn WAInjectBench Validation Checkpoint Selection
- Principle:OpenRLHF OpenRLHF KL Divergence Estimation
Implementations
- Implementation:Pyro ppl Pyro NeuTra
- Implementation:Online ml River Bandit Datasets Base
- Implementation:MaterializeInc Materialize Lint Manager
- Implementation:Langgenius Dify I18n Dataset Documents Translations
- Implementation:Astronomer Astronomer cosmos Graph Entities
- Implementation:Kubeflow Pipelines Regression Metrics Evaluation
- Implementation:NVIDIA DALI PluginManager
- Implementation:Online ml River Time Series HoltWinters
- Implementation:Triton inference server Server L0 Opentelemetry Unittest
- Implementation:Datajuicer Data juicer DataValidator
Heuristics
- Heuristic:Explodinggradients Ragas Failed Metrics Return NaN
- Heuristic:Nautechsystems Nautilus trader Streaming Mode For Large Backtests
- Heuristic:Unstructured IO Unstructured Golden File Diff
- Heuristic:SeleniumHQ Selenium Warning Deprecated Proxy FTP Methods
- Heuristic:AnswerDotAI RAGatouille Collection Size Index Tuning
- Heuristic:Liu00222 Open Prompt Injection BPE Retokenization Parameters
- Heuristic:Vespa engine Vespa Maven Parallel Build Optimization
- Heuristic:Facebookresearch Audiocraft Chroma Conditioning Cache Requirement
- Heuristic:Openai CLIP CLIP Normalization Constants
- Heuristic:TobikoData Sqlmesh Execution Time Caching
Environments
- Environment:NVIDIA DALI CMake Build Environment
- Environment:Openai Openai python Python 3 9 Plus
- Environment:Snorkel team Snorkel PyTorch
- Environment:Shiyu coder Kronos DDP Multi GPU Environment
- Environment:Google deepmind Mujoco Python Bindings Environment
- Environment:Ggml org Llama cpp Python Conversion Environment
- Environment:Explodinggradients Ragas Google Drive Backend Environment
- Environment:Microsoft Onnxruntime Windows Build Environment
- Environment:Neuml Txtai API Server Configuration
- Environment:TobikoData Sqlmesh Web UI Stack