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:Bigscience workshop Petals Distributed Text Generation
- Workflow:SeleniumHQ Selenium Contributor Development Workflow
- Workflow:ARISE Initiative Robosuite Gymnasium RL Integration
- Workflow:DevExpress Testcafe CI Integration
- Workflow:ARISE Initiative Robosuite Human Demonstration Collection
- Workflow:Intel Ipex llm LoRA Finetuning
- Workflow:Langgenius Dify Workflow Builder and Execution
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:Zai org CogVideo SAT Finetuning
- Workflow:CARLA simulator Carla Simulation Setup and First Steps
Principles
- Principle:Langgenius Dify CSP Policy
- Principle:OpenHands OpenHands Conversation Initiation
- Principle:Confident ai Deepeval Conversation Simulation
- Principle:Neuml Txtai Text Extraction
- Principle:Groq Groq python Streaming Request Execution
- Principle:Langfuse Langfuse Prompt Retrieval and Resolution
- Principle:Microsoft Onnxruntime Checkpoint Loading
- Principle:Ggml org Llama cpp Batch Processing System
- Principle:Microsoft Playwright Execute API Requests
- Principle:Princeton nlp SimPO Chat Template Application
Implementations
- Implementation:Microsoft Onnxruntime Npm Install Onnxruntime
- Implementation:ArroyoSystems Arroyo Catalog Component
- Implementation:Pyro ppl Pyro NanMaskedDistributions
- Implementation:NVIDIA NeMo Curator DuplicateRemovalStage
- Implementation:Haosulab ManiSkill GoogleRobot
- Implementation:NVIDIA NeMo Curator BaseClassifierStage
- Implementation:Heibaiying BigData Notes StreamExecutionEnvironment GetExecutionEnvironment
- Implementation:Langgenius Dify UsePublishWorkflow
- Implementation:Teamcapybara Capybara Node Matchers Assert Selector
- Implementation:Cohere ai Cohere python SSE EventSource
Heuristics
- Heuristic:FlagOpen FlagEmbedding Length Sorted Batching
- Heuristic:Obss Sahi Warning Deprecated Legacy NMS
- Heuristic:OpenGVLab InternVL Gradient Checkpointing Memory
- Heuristic:Open compass VLMEvalKit SKIP ERR For Graceful Inference
- Heuristic:NVIDIA DALI Memory Pool Tuning
- Heuristic:Apache Dolphinscheduler Failover Marker TTL
- Heuristic:LaurentMazare Tch rs Device Fallback Pattern
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Neuml Txtai Batch Size Defaults
- Heuristic:Intel Ipex llm Use Cache Training Vs Inference
Environments
- Environment:DataTalksClub Data engineering zoomcamp Dlt BigQuery Environment
- Environment:Deepseek ai Janus JanusFlow Diffusers Environment
- Environment:Huggingface Datasets Audio Video Dependencies
- Environment:Shiyu coder Kronos Qlib Data Environment
- Environment:Huggingface Trl PEFT LoRA Environment
- Environment:Anthropics Anthropic sdk python Azure Foundry Environment
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:Puppeteer Puppeteer Cross Platform Browser Environment
- Environment:BerriAI Litellm Provider API Credentials
- Environment:Dotnet Machinelearning ONNX Runtime Environment