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:Huggingface Peft LoRA Embedding Semantic Search
- Workflow:MaterializeInc Materialize Upgrade Testing
- Workflow:CarperAI Trlx PPO Sentiment Training
- Workflow:Apache Hudi Flink Batch Incremental Read
- Workflow:Openai Openai agents python Guardrails Secured Agent
- Workflow:Datahub project Datahub Spark Lineage Capture
- Workflow:MaterializeInc Materialize Release Process
- Workflow:MarketSquare Robotframework browser API Testing via Browser
- Workflow:Hiyouga LLaMA Factory Full Parameter SFT
- Workflow:Huggingface Peft Prompt Tuning Classification
Principles
- Principle:Junyanz Pytorch CycleGAN and pix2pix Unpaired Image Translation
- Principle:Groq Groq python Batch Status Polling
- Principle:Puppeteer Puppeteer Request Interception
- Principle:Microsoft BIPIA Clean Response Collection
- Principle:LaurentMazare Tch rs Tensor Indexing Operations
- Principle:Openclaw Openclaw Channel Setup
- Principle:Vespa engine Vespa Log Target and Level Configuration
- Principle:Deepspeedai DeepSpeed Hybrid Engine Init
- Principle:Online ml River Incremental Clustering Interface
- Principle:Huggingface Optimum Export Configuration Construction
Implementations
- Implementation:Online ml River Metrics GeometricMean
- Implementation:Openai Openai node Transcriptions Create
- Implementation:Langchain ai Langchain PyPI Trusted Publishing Production
- Implementation:Apache Druid Aggregate Macro
- Implementation:Mlc ai Mlc llm Model Metadata Impl
- Implementation:Langfuse Langfuse Eval JSONPath Extraction Utilities
- Implementation:PrefectHQ Prefect Pause Flow Run
- Implementation:Gretelai Gretel synthetics ACTGANSynthesizer Actual Fit
- Implementation:BerriAI Litellm Managed Files
- Implementation:HKUDS AI Trader Jina Search Tool
Heuristics
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix High Res Crop Training
- Heuristic:Spotify Luigi Marker Table Idempotency
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:Langchain ai Langchain Retry Scope Best Practice
- Heuristic:Microsoft Semantic kernel Prompt Injection Safety
- Heuristic:Alibaba ROLL Sequence Packing Alignment
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Trailofbits Fickling Injection Mode Selection
- Heuristic:ArroyoSystems Arroyo Async UDF Concurrency
- Heuristic:PeterL1n BackgroundMattingV2 Training Batch Size And Resolution
Environments
- Environment:Truera Trulens LangChain LangGraph Environment
- Environment:InternLM Lmdeploy CUDA GPU Runtime
- Environment:Promptfoo Promptfoo Provider API Keys
- Environment:Microsoft Autogen Python Runtime Environment
- Environment:Apache Beam Java Build Environment
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Iterative Dvc DVC Environment Variables
- Environment:Isaac sim IsaacGymEnvs Pip Dependencies
- Environment:Microsoft DeepSpeedExamples CIFAR10 Training Environment
- Environment:Haotian liu LLaVA Python CUDA Training Environment