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:PrefectHQ Prefect Per Worker Task Concurrency
- Workflow:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:Openai Openai agents python Tool Integrated Agent
- Workflow:Run llama Llama index Data Ingestion Pipeline
- Workflow:DataExpert io Data engineer handbook AB Experimentation Server
- Workflow:ARISE Initiative Robosuite Domain Randomization Training
- Workflow:Lm sys FastChat ShareGPT Data Pipeline
- Workflow:Langfuse Langfuse Batch export pipeline
- Workflow:Treeverse LakeFS S3 Gateway Integration
- Workflow:Microsoft Agent framework Agent With Tool Approval
Principles
- Principle:Openai Openai agents python Hosted Tool Configuration
- Principle:Langgenius Dify Application Publishing
- Principle:Tensorflow Serving Dependency Ownership
- Principle:Mage ai Mage ai Paginated SQL Extraction
- Principle:Huggingface Diffusers Scheduler Selection
- Principle:Huggingface Datatrove LLM Inference Execution
- Principle:Huggingface Datatrove Duplicate Clustering
- Principle:Langgenius Dify Annotation System
- Principle:Webdriverio Webdriverio ErrorHandling
- Principle:Google deepmind Mujoco Restrict Optimization
Implementations
- Implementation:Bigscience workshop Petals Dataset Loading Pipeline
- Implementation:Puppeteer Puppeteer Cdp ExtensionTransport
- Implementation:LMCache LMCache Fast Serde
- Implementation:Triton inference server Server Launch Triton Server Script
- Implementation:Open compass VLMEvalKit DoubaoVLWrapper
- Implementation:Run llama Llama index PromptMixin
- Implementation:Nightwatchjs Nightwatch Gherkin Feature Syntax
- Implementation:Google deepmind Mujoco mj saveModel
- Implementation:Kserve Kserve AnchorText Explainer
- Implementation:Huggingface Datatrove KenlmModel
Heuristics
- Heuristic:Sktime Pytorch forecasting Encoder Decoder Length Limits
- Heuristic:Alibaba MNN Warning Deprecated Winograd Codegen
- Heuristic:Nautechsystems Nautilus trader Parquet Row Group Tuning
- Heuristic:Interpretml Interpret EBM Hyperparameter Tuning Guide
- Heuristic:Huggingface Peft LoRA Initialization Strategy Selection
- Heuristic:Wandb Weave Retry And Error Handling
- Heuristic:Langfuse Langfuse ClickHouse FINAL Skip Optimization
- Heuristic:Alibaba ROLL Reward Clipping Normalization
- Heuristic:AnswerDotAI RAGatouille FAISS Vs PyTorch KMeans Indexing
- Heuristic:Mlfoundations Open flamingo Hungarian MMC4 Image Text Matching
Environments
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:Vllm project Vllm Environment Variables
- Environment:Microsoft Semantic kernel ONNX CUDA Environment
- Environment:Deepspeedai DeepSpeed Python Runtime Environment
- Environment:Microsoft Autogen Studio Server Environment
- Environment:Bigscience workshop Petals CUDA Server
- Environment:Fastai Fastbook Sklearn Environment
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Apache Druid Druid Cluster Api
- Environment:Openai Evals Optional Provider APIs