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 — full-stack AI/ML coding agent
- Leeroopedia MCP — knowledge search for any coding agent
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:Predibase Lorax Structured JSON Output
- Workflow:Googleapis Python genai Context Caching
- Workflow:Kornia Kornia Image Feature Matching
- Workflow:Guardrails ai Guardrails Structured Data Generation
- Workflow:Datahub project Datahub Spark Lineage Capture
- Workflow:Tencent Ncnn Post Training Quantization
- Workflow:Apache Dolphinscheduler Workflow Failover Recovery
- Workflow:Langchain ai Langgraph Functional API Workflow
- Workflow:Neuml Txtai API Deployment
- Workflow:Unstructured IO Unstructured Document Partitioning
Principles
- Principle:Online ml River Online Ensemble Methods
- Principle:Apache Kafka Maven Artifact Publishing
- Principle:Pola rs Polars Time Range Filtering
- Principle:Huggingface Datasets SQL Import
- Principle:Truera Trulens Context Filter Guardrail
- Principle:Online ml River TextClust Clustering
- Principle:Confident ai Deepeval Offline Trace Evaluation
- Principle:Pyro ppl Pyro Funsor Backend HMM
- Principle:Neuml Txtai Workflow Composition
- Principle:Online ml River Online One Class SVM
Implementations
- Implementation:Mage ai Mage ai Chargebee Client
- Implementation:CARLA simulator Carla Client Set Replayer Time Factor
- Implementation:Apache Kafka Connect Distributed Script
- Implementation:Microsoft Playwright TraceV7
- Implementation:Microsoft DeepSpeedExamples Create Critic Model
- Implementation:NVIDIA DALI Cpplint
- Implementation:Ucbepic Docetl Dataset Debate Gleaning
- Implementation:Run llama Llama index BaseObjectNodeMapping
- Implementation:SeleniumHQ Selenium Bootstrap Main Entry
- Implementation:Allenai Open instruct TensorCache
Heuristics
- Heuristic:ARISE Initiative Robomimic BatchNorm To GroupNorm For EMA
- Heuristic:Dagster io Dagster Mandatory Ruff Formatting
- Heuristic:Sail sg LongSpec Triton Block Size Tuning
- Heuristic:Facebookresearch Audiocraft Gradient Balancing For Multi Loss
- Heuristic:BerriAI Litellm Connection Pooling Memory Management
- Heuristic:Online ml River SNARIMAX Default Regressor Pipeline
- Heuristic:Langchain ai Langgraph Recursion Limit Tuning
- Heuristic:Promptfoo Promptfoo Retry With Jitter
- Heuristic:Spotify Luigi Marker Table Idempotency
- Heuristic:Openai CLIP CLIP Normalization Constants
Environments
- Environment:HKUDS AI Trader API Credentials
- Environment:Spotify Luigi SQLAlchemy Database
- Environment:Huggingface Peft GPU Hardware Detection
- Environment:Googleapis Python genai Python 3 10 SDK Runtime
- Environment:PacktPublishing LLM Engineers Handbook AWS SageMaker GPU Environment
- Environment:Openai CLIP Python Dependencies
- Environment:Puppeteer Puppeteer Configuration Environment Variables
- Environment:Vibrantlabsai Ragas LLM Provider Credentials
- Environment:OpenRLHF OpenRLHF Flash Attention Environment
- Environment:Gretelai Gretel synthetics Python Base Environment