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:Diagram of thought Diagram of thought DoT Trace Extraction
- Workflow:NVIDIA NeMo Aligner Supervised Fine Tuning
- Workflow:Anthropics Anthropic sdk python Streaming Message Interaction
- Workflow:Neuml Txtai Agent Execution
- Workflow:Volcengine Verl GRPO Training Pipeline
- Workflow:OpenHands OpenHands Conversation Lifecycle Management
- Workflow:Avdvg InjectGuard Vector Similarity Detection Pipeline
- Workflow:Openai Evals Creating a model graded eval
- Workflow:Vllm project Vllm Offline Text Generation
- Workflow:LLMBook zh LLMBook zh github io Supervised Finetuning
Principles
- Principle:Nightwatchjs Nightwatch Cucumber Dependency Setup
- Principle:Puppeteer Puppeteer Data Extraction
- Principle:Turboderp org Exllamav2 Layer Normalization
- Principle:Facebookresearch Habitat lab Dataset and Scene Preparation
- Principle:CrewAIInc CrewAI Task Replay
- Principle:Huggingface Datasets HDF5 Dataset Building
- Principle:HKUDS AI Trader Frontend Data Loading
- Principle:Openai CLIP Top K Accuracy Evaluation
- Principle:Intel Ipex llm Document Chunking
- Principle:Huggingface Alignment handbook Direct Preference Optimization
Implementations
- Implementation:SeleniumHQ Selenium NetworkInterceptor Constructor
- Implementation:OpenGVLab InternVL Evaluate Sh
- Implementation:Open compass VLMEvalKit RBdashMMChat3Wrapper
- Implementation:Hpcaitech ColossalAI AGIEvalDataset
- Implementation:Alibaba MNN Protobuf Reflection H
- Implementation:Infiniflow Ragflow ChildrenDelimiterForm Component
- Implementation:Huggingface Diffusers ControlNetModel From Pretrained
- Implementation:Datahub project Datahub EntityClient Upsert
- Implementation:EvolvingLMMs Lab Lmms eval VideoMathQA CoT Postprocess
- Implementation:Lucidrains X transformers XTransformer Generate
Heuristics
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:Isaac sim IsaacGymEnvs JIT Profiling Optimization
- Heuristic:Sktime Pytorch forecasting Encoder Decoder Length Limits
- Heuristic:Google deepmind Dm control Tolerance Reward Tuning
- Heuristic:Tensorflow Serving Servable Handle Lifetime
- Heuristic:Roboflow Rf detr Batch Size Memory Tradeoff
- Heuristic:EvolvingLMMs Lab Lmms eval Truncated Image Handling
- Heuristic:Teamcapybara Capybara Negative Predicate Matching
- Heuristic:Huggingface Datasets Shuffle Buffer Sizing
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
Environments
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Open compass VLMEvalKit Data Storage Environment
- Environment:Getgauge Taiko Node Runtime
- Environment:Microsoft Semantic kernel OpenAI API Environment
- Environment:Nightwatchjs Nightwatch Android Mobile Testing
- Environment:Vllm project Vllm AMD ROCm
- Environment:Bitsandbytes foundation Bitsandbytes ROCm AMD Environment
- Environment:Microsoft Semantic kernel ONNX CUDA Environment
- Environment:AnswerDotAI RAGatouille GPU CUDA Runtime
- Environment:OpenHands OpenHands Third Party Runtime Credentials