Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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 BIPIA Black Box Defense Evaluation
- Workflow:Haotian liu LLaVA LoRA Finetuning
- Workflow:Datahub project Datahub CLI Metadata Ingestion
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
- Workflow:Helicone Helicone Integrate Provider To Gateway
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:Huggingface Trl PPO RLHF Training
- Workflow:ClickHouse ClickHouse Server Deployment
- Workflow:DevExpress Testcafe CI Integration
- Workflow:Puppeteer Puppeteer Page Screenshot Capture
Principles
- Principle:OpenHands OpenHands Middleware Configuration
- Principle:SeleniumHQ Selenium Element Caching Strategy
- Principle:Langchain ai Langchain Package Scaffolding
- Principle:NVIDIA DALI PyTorch Training Integration
- Principle:Huggingface Trl PPO Argument Configuration
- Principle:AnswerDotAI RAGatouille Trainer Initialization
- Principle:Cohere ai Cohere python Tool Function Execution
- Principle:Iterative Dvc Experiment Apply Or Discard
- Principle:AUTOMATIC1111 Stable diffusion webui Transformer Diffusion Architecture
- Principle:Datajuicer Data juicer QA Optimization
Implementations
- Implementation:BerriAI Litellm Email Alert Types
- Implementation:FlowiseAI Flowise SamplePromptDialog
- Implementation:HKUDS AI Trader Frontend Config YAML
- Implementation:Evidentlyai Evidently Dashboard Panels
- Implementation:Promptfoo Promptfoo applyStrategies
- Implementation:Lance format Lance Java RestNamespace
- Implementation:DataExpert io Data engineer handbook Statsig Initialize
- Implementation:Mlc ai Mlc llm Radix Tree
- Implementation:NVIDIA DALI C API V2 Pipeline
- Implementation:Promptfoo Promptfoo Environment Variables
Heuristics
- Heuristic:Rapidsai Cuml Quantile Split Differences
- Heuristic:Zai org CogVideo CPU Offload Strategy
- Heuristic:LLMBook zh LLMBook zh github io Reward Model LM Regularization
- Heuristic:Unslothai Unsloth LoRA Rank Selection
- Heuristic:Eric mitchell Direct preference optimization FSDP Mixed Precision BFloat16
- Heuristic:Lucidrains X transformers Flash Attention Configuration
- Heuristic:Microsoft Playwright Timeout Configuration Tips
- Heuristic:Openai Openai python Fine Tuning Data Preparation Tips
- Heuristic:OpenHands OpenHands Fail Open Rate Limiting
- Heuristic:Huggingface Datasets Batch Size Optimization
Environments
- Environment:Onnx Onnx Python Runtime Environment
- Environment:Avhz RustQuant Rust Stable
- Environment:Huggingface Optimum GPTQ Quantization Environment
- Environment:Microsoft DeepSpeedExamples RLHF Training Environment
- Environment:LMCache LMCache Python Runtime
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:LLMBook zh LLMBook zh github io Data Processing Environment
- Environment:NVIDIA DALI FFmpeg Environment
- Environment:Apache Hudi Flink Runtime Environment
- Environment:Facebookresearch Habitat lab HITL Runtime Environment