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:MarketSquare Robotframework browser API Testing via Browser
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Avdvg InjectGuard Vector Similarity Detection Pipeline
- Workflow:Alibaba ROLL Knowledge Distillation Pipeline
- Workflow:Huggingface Peft DreamBooth LoRA Diffusion
- Workflow:OWASP Www project top 10 for large language model applications Agentic Security Assessment
- Workflow:Recommenders team Recommenders Neural Collaborative Filtering
- Workflow:Run llama Llama index ReAct Agent
- Workflow:OpenGVLab InternVL Benchmark Evaluation
Principles
- Principle:Confident ai Deepeval Retriever Span Enrichment
- Principle:Pola rs Polars Query Plan Inspection
- Principle:Guardrails ai Guardrails Stream Chunk Processing
- Principle:Langgenius Dify Frontend Architecture
- Principle:Huggingface Datatrove Data Reading Framework
- Principle:Huggingface Datatrove Token Counting
- Principle:Online ml River Streaming Classification Metrics
- Principle:FlowiseAI Flowise Variable Management
- Principle:Alibaba MNN Diffusion Inference Execution
- Principle:SeleniumHQ Selenium PageFactory Initialization
Implementations
- Implementation:ARISE Initiative Robosuite Reset From Xml String
- Implementation:Langfuse Langfuse API Dataset Items Schema
- Implementation:Princeton nlp Tree of thought llm Solve BFS
- Implementation:Kornia Kornia SSIM Metric
- Implementation:Ollama Ollama Imagegen Engine Main
- Implementation:Promptfoo Promptfoo Plugins Data Catalog
- Implementation:Neuml Txtai RetrieveTask
- Implementation:Facebookresearch Habitat lab Agent ABC
- Implementation:Diagram of thought Diagram of thought Rigor Protocol Configuration
- Implementation:LLMBook zh LLMBook zh github io Encode With BPE
Heuristics
- Heuristic:Apache Shardingsphere Shadow Routing Hint First Fallback
- Heuristic:ArroyoSystems Arroyo Stateful Operator TTL
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:ArroyoSystems Arroyo Batch Size And Backpressure
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
- Heuristic:Spotify Luigi Dynamic Requirements Generator
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:Mlfoundations Open flamingo FSDP Manual Wrapping For Mixed Parameters
- Heuristic:Obss Sahi Class Agnostic vs Per Class NMS
- Heuristic:AnswerDotAI RAGatouille In Memory Reranking Limits
Environments
- Environment:TobikoData Sqlmesh Dbt Compatibility
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Vibrantlabsai Ragas Python 3 9 Core Environment
- Environment:Lucidrains X transformers PyTorch CUDA
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:Bitsandbytes foundation Bitsandbytes Build From Source Environment
- Environment:Marker Inc Korea AutoRAG VLLM Environment
- Environment:Sktime Pytorch forecasting Optuna Tuning Dependencies
- Environment:Openai Openai python Voice Helpers
- Environment:Pola rs Polars Cloud Storage Environment