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:Huggingface Datatrove Summary Statistics
- Workflow:Pola rs Polars Lazy Query Pipeline
- Workflow:Huggingface Datasets Dataset Loading and Exploration
- Workflow:ARISE Initiative Robosuite Environment Setup And Simulation
- Workflow:Cleanlab Cleanlab Classification Label Issue Detection
- Workflow:Obss Sahi Sliced Inference Pipeline
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Promptfoo Promptfoo Project Initialization
- Workflow:FlagOpen FlagEmbedding Benchmark Evaluation
Principles
- Principle:Google deepmind Mujoco Newton Solver
- Principle:DataTalksClub Data engineering zoomcamp Kestra Table Creation
- Principle:Langchain ai Langgraph UI Component Management
- Principle:Langgenius Dify Dynamic Import Pattern
- Principle:Microsoft Semantic kernel Vector Store Collection Setup
- Principle:Ggml org Llama cpp Text Processing
- Principle:LaurentMazare Tch rs Weight Loading
- Principle:Neuml Txtai YAML Application Configuration
- Principle:DataExpert io Data engineer handbook Test Data Construction
- Principle:ClickHouse ClickHouse Portable Atomic Operations
Implementations
- Implementation:PacktPublishing LLM Engineers Handbook SFTTrainer Train
- Implementation:Alibaba MNN LLM Config JSON
- Implementation:Turboderp org Exllamav2 Ext QMLP
- Implementation:SeleniumHQ Selenium Closure Log
- Implementation:Tencent Ncnn YOLOv8 Pose Example
- Implementation:Roboflow Rf detr Best Checkpoint Selection
- Implementation:Ollama Ollama ParseFromModel
- Implementation:Microsoft Playwright StackTrace
- Implementation:FlagOpen FlagEmbedding BGE Eval MSMARCO
- Implementation:Apache Airflow TimerProtocol
Heuristics
- Heuristic:Huggingface Diffusers Guidance Scale Defaults
- Heuristic:CrewAIInc CrewAI MCP Timeout And Retry Strategy
- Heuristic:Haosulab ManiSkill Initial Pose Performance
- Heuristic:Interpretml Interpret Memory Budget Heuristic
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:Evidentlyai Evidently Statistical Test Auto Selection
- Heuristic:Huggingface Datatrove VLLM Startup Optimization
- Heuristic:Ray project Ray Autoscaling Delay Tuning
- Heuristic:Getgauge Taiko Browser Launch Flags
- Heuristic:Langgenius Dify Gevent Monkey Patching Order
Environments
- Environment:Heibaiying BigData Notes HBase Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Nautechsystems Nautilus trader Databento API Credentials
- Environment:Allenai Open instruct Ray Distributed
- Environment:Unslothai Unsloth Python Transformers
- Environment:Interpretml Interpret Visualization Environment
- Environment:Heibaiying BigData Notes Kafka 2 2 Environment
- Environment:Huggingface Open r1 CUDA Environment
- Environment:Sgl project Sglang CUDA SM100
- Environment:Shiyu coder Kronos Comet ML Logging