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:DataExpert io Data engineer handbook Dimensional Data Modeling Environment Setup
- Workflow:Romsto Speculative Decoding Speculative Decoding Inference
- Workflow:Ggml org Llama cpp Model Perplexity Evaluation
- Workflow:MarketSquare Robotframework browser API Testing via Browser
- Workflow:Heibaiying BigData Notes Storm Topology Development
- Workflow:AnswerDotAI RAGatouille In Memory Retrieval
- Workflow:ArroyoSystems Arroyo Local Pipeline Execution
- Workflow:Langgenius Dify Knowledge Base Creation
- Workflow:Kubeflow Pipelines Pipeline Authoring and Compilation
- Workflow:TobikoData Sqlmesh Dbt project migration
Principles
- Principle:Haifengl Smile SQL Database Connection
- Principle:Ollama Ollama ServerArchitecture
- Principle:Predibase Lorax HTTP Client Connection
- Principle:Duckdb Duckdb Prerequisite Code Generation
- Principle:Google deepmind Dm control Multi Agent Episode Loop
- Principle:PacktPublishing LLM Engineers Handbook HuggingFace Dataset Publishing
- Principle:Lm sys FastChat Battle Data Cleaning
- Principle:ThreeSR Awesome Inference Time Scaling Paper Entry Formatting
- Principle:Microsoft Autogen Function Tool Definition
- Principle:Vllm project Vllm LLM Engine Initialization
Implementations
- Implementation:Marker Inc Korea AutoRAG Factoid Query Gen
- Implementation:Microsoft Semantic kernel ChatCompletionAgent
- Implementation:Hiyouga LLaMA Factory VLLM Engine
- Implementation:Scikit learn Scikit learn GraphicalLasso
- Implementation:Explodinggradients Ragas MemorableNames Class
- Implementation:Evidentlyai Evidently Metric Types
- Implementation:Ray project Ray Release Data Tests Config
- Implementation:Astronomer Astronomer cosmos Cloud Storage Connection Setup
- Implementation:Ggml org Ggml Cpu weight repack
- Implementation:Microsoft Playwright BidiSerializer
Heuristics
- Heuristic:Unslothai Unsloth Gradient Checkpointing Modes
- Heuristic:Treeverse LakeFS Retry Backoff Configuration
- Heuristic:Danijar Dreamerv3 Percentile Return Normalization
- Heuristic:Cypress io Cypress Xvfb Display Gotcha
- Heuristic:Online ml River SNARIMAX Default Regressor Pipeline
- Heuristic:Microsoft Agent framework Silent Workflow Failures
- Heuristic:Duckdb Duckdb Memory Management Rules
- Heuristic:Sktime Pytorch forecasting Gradient Clipping Value
- Heuristic:Unstructured IO Unstructured Hi Res Model Configuration
- Heuristic:Alibaba ROLL Reward Clipping Normalization
Environments
- Environment:Dotnet Machinelearning Native Build Toolchain
- Environment:SeldonIO Seldon core Kubernetes Cluster Environment
- Environment:Evidentlyai Evidently Python Core Environment
- Environment:Apache Dolphinscheduler Netty Runtime
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Deepset ai Haystack OpenAI API Environment
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Haosulab ManiSkill Real Robot LeRobot Deps
- Environment:Guardrails ai Guardrails Python 3 10 Runtime
- Environment:Groq Groq python Python Groq SDK