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:Deepspeedai DeepSpeed Inference Engine Optimization
- Workflow:OpenGVLab InternVL Multi Stage Pretraining
- Workflow:Mlc ai Mlc llm REST API Serving
- Workflow:Alibaba MNN Python Model Inference
- Workflow:LLMBook zh LLMBook zh github io DPO Alignment
- Workflow:Datajuicer Data juicer LLM Powered Data Generation
- Workflow:Interpretml Interpret EBM Model Merging
- Workflow:Langchain ai Langchain Chat Model Invocation
- Workflow:FlowiseAI Flowise Chatbot Deployment
- Workflow:DistrictDataLabs Yellowbrick Regression Model Evaluation
Principles
- Principle:Gretelai Gretel synthetics WGAN GP Training
- Principle:Duckdb Duckdb FSST String Compression
- Principle:Evidentlyai Evidently Dashboard Panel Configuration
- Principle:Huggingface Alignment handbook LoRA Adapter Configuration
- Principle:Groq Groq python Audio Transcription Request
- Principle:Huggingface Datasets Hub Metadata Configs
- Principle:Microsoft DeepSpeedExamples DeepSpeed Engine Init
- Principle:Mlflow Mlflow Code Quality Linting
- Principle:SeldonIO Seldon core V2 Inference Protocol
- Principle:Infiniflow Ragflow Graph State Management
Implementations
- Implementation:Explodinggradients Ragas AgentGoalAccuracy Metric
- Implementation:Lance format Lance Chunker
- Implementation:Apache Paimon FunctionDefinition
- Implementation:Infiniflow Ragflow LargeModelFormField Component
- Implementation:Cohere ai Cohere python GetModelResponse Model
- Implementation:Webdriverio Webdriverio Config Constants
- Implementation:Apache Paimon RESTApi
- Implementation:Mlc ai Mlc llm Result Type
- Implementation:Openai Openai agents python MCP Approval Callback Pattern
- Implementation:Ollama Ollama Imagegen Transfer
Heuristics
- Heuristic:Testtimescaling Testtimescaling github io Skip CI Commit Tag
- Heuristic:Heibaiying BigData Notes Hive ORC Parquet Storage Tip
- Heuristic:Huggingface Peft Gradient Checkpointing With Quantization
- Heuristic:Facebookresearch Habitat lab Force Single Threaded PyTorch
- Heuristic:Mistralai Client python Tool Docstring Requirement
- Heuristic:AnswerDotAI RAGatouille Collection Size Index Tuning
- Heuristic:Iamhankai Forest of Thought Tree Iteration Scaling
- Heuristic:Openai CLIP Class Name Curation
- Heuristic:OpenGVLab InternVL LoRA Alpha Scaling
- Heuristic:AUTOMATIC1111 Stable diffusion webui Cross Attention Memory Slicing
Environments
- Environment:Apache Dolphinscheduler Java Runtime
- Environment:FlagOpen FlagEmbedding GPU Accelerator Environment
- Environment:Snorkel team Snorkel Dask Distributed
- Environment:SeleniumHQ Selenium Contributor Development Environment
- Environment:Apache Druid Integration Test Docker
- Environment:Scikit learn Scikit learn Python Runtime Environment
- Environment:Scikit learn contrib Imbalanced learn Python Scikit learn
- Environment:Gretelai Gretel synthetics TensorFlow GPU Environment
- Environment:Deepseek ai Janus CUDA GPU Environment
- Environment:FlowiseAI Flowise Database Environment