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:NVIDIA DALI Video Processing Pipeline
- Workflow:Treeverse LakeFS Write Audit Publish With Hooks
- Workflow:Nightwatchjs Nightwatch E2E Test Authoring
- Workflow:TobikoData Sqlmesh Github CICD automation
- Workflow:NVIDIA DALI Object Detection Training TensorFlow
- Workflow:Liu00222 Open Prompt Injection Prompt Injection Experiment
- Workflow:MaterializeInc Materialize CI Pipeline Generation
- Workflow:Arize ai Phoenix Dataset and Experiment Lifecycle
- Workflow:Puppeteer Puppeteer Request Interception
- Workflow:Huggingface Trl Supervised Finetuning
Principles
- Principle:Eventual Inc Daft Data Preprocessing Regex Extraction
- Principle:Langchain ai Langgraph Project Configuration
- Principle:LaurentMazare Tch rs Top K Prediction
- Principle:Langgenius Dify PromptEngineering
- Principle:Langgenius Dify App Initialization
- Principle:PacktPublishing LLM Engineers Handbook SageMaker Evaluation Orchestration
- Principle:Huggingface Datasets Extension Module Mapping
- Principle:Kubeflow Kubeflow Build Pipeline
- Principle:OpenRLHF OpenRLHF Dataset Blending
- Principle:Apache Beam Pipeline Construction
Implementations
- Implementation:Helicone Helicone Prompt Types
- Implementation:DistrictDataLabs Yellowbrick ConfusionMatrix Visualizer
- Implementation:Explodinggradients Ragas OCIGenAIWrapper Class
- Implementation:Interpretml Interpret LimeTabular
- Implementation:Webdriverio Webdriverio Gherkin Syntax Pattern
- Implementation:Marker Inc Korea AutoRAG Runner Init
- Implementation:Apache Paimon SchemaChange
- Implementation:Vibrantlabsai Ragas InstanceRubrics
- Implementation:Helicone Helicone BuildRouter
- Implementation:Princeton nlp Tree of thought llm Gpt Usage
Heuristics
- Heuristic:Dotnet Machinelearning Sparsity Threshold Optimization
- Heuristic:LLMBook zh LLMBook zh github io Greedy Decoding Temperature Zero
- Heuristic:Tencent Ncnn Thread Count Tuning
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
- Heuristic:Scikit learn Scikit learn N Jobs Parallelism Tips
- Heuristic:Openai Openai agents python Default Max Turns Safety Limit
- Heuristic:Apache Flink Bin Packing Complexity Guard
- Heuristic:EvolvingLMMs Lab Lmms eval Distributed Padding Strategy
- Heuristic:Openclaw Openclaw Retry With Exponential Backoff
- Heuristic:OpenGVLab InternVL Pixel Shuffle Downsampling
Environments
- Environment:Kserve Kserve VLLM Runtime
- Environment:Togethercomputer Together python Python SDK Runtime
- Environment:Sail sg LongSpec Training Environment
- Environment:Alibaba MNN HuggingFace Ecosystem Environment
- Environment:SeldonIO Seldon core Docker Compose Local Environment
- Environment:Kornia Kornia PyTorch Python Environment
- Environment:Intel Ipex llm Windows Environment
- Environment:Sgl project Sglang Web
- Environment:Tensorflow Tfjs Python Converter
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference