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:Microsoft Autogen Swarm Agent Handoff
- Workflow:PrefectHQ Prefect Database Cleanup With Approval
- Workflow:Eric mitchell Direct preference optimization DPO Preference Training
- Workflow:Duckdb Duckdb Building From Source
- Workflow:EvolvingLMMs Lab Lmms eval Custom Model Integration
- Workflow:Huggingface Trl Reward Model Training
- Workflow:DistrictDataLabs Yellowbrick Regression Model Evaluation
- Workflow:Tencent Ncnn PyTorch Model Conversion and Inference
- Workflow:Allenai Open instruct Tulu3 Full Post Training
- Workflow:Kubeflow Kubeflow Contributing To Kubeflow
Principles
- Principle:Huggingface Optimum GPTQ Post Initialization
- Principle:Openai Openai agents python Function Tool Definition
- Principle:Risingwavelabs Risingwave CDC Source Database Preparation
- Principle:Spotify Luigi Hive Data Access
- Principle:Apache Spark K8s Prerequisites Verification
- Principle:Anthropics Anthropic sdk python Message Request Construction
- Principle:Huggingface Datasets Language Code Registry
- Principle:Ollama Ollama MLXRunner Architecture
- Principle:Sgl project Sglang Distributed Environment Setup
- Principle:Microsoft Autogen Tool Execution Loop
Implementations
- Implementation:Promptfoo Promptfoo SharePoint Integration
- Implementation:Pyro ppl Pyro ReplayMessenger
- Implementation:Ggml org Llama cpp GGUF Split
- Implementation:Confident ai Deepeval DocumentChunker
- Implementation:Google deepmind Mujoco Engine Util Solve
- Implementation:OpenGVLab InternVL Internvl Custom2hf
- Implementation:Run llama Llama index Pooling
- Implementation:ArroyoSystems Arroyo Iceberg Transforms
- Implementation:Teamcapybara Capybara Selector Button
- Implementation:Online ml River Stats Mean
Heuristics
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Dagster io Dagster Lazy Import Pattern
- Heuristic:DataExpert io Data engineer handbook Watermark Late Arrival Tolerance
- Heuristic:Hiyouga LLaMA Factory Quantized Training Best Practices
- Heuristic:Zai org CogVideo DeepSpeed Checkpoint Conversion Tips
- Heuristic:Shiyu coder Kronos Two Stage Finetuning Strategy
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:EvolvingLMMs Lab Lmms eval Limit Flag Testing Only
- Heuristic:Lance format Lance Warning Deprecated Legacy Encodings
- Heuristic:Langchain ai Langchain Error Context Preservation
Environments
- Environment:Neuml Txtai GPU Accelerator Detection
- Environment:HKUDS AI Trader API Credentials
- Environment:Langfuse Langfuse Node 24 Runtime
- Environment:ArroyoSystems Arroyo Rust Runtime
- Environment:Cohere ai Cohere python AWS Integration Dependencies
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:PacktPublishing LLM Engineers Handbook API Credentials
- Environment:Apache Druid Druid Operator Kubernetes
- Environment:OpenRLHF OpenRLHF Flash Attention Environment
- Environment:OpenRLHF OpenRLHF CUDA GPU Environment