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:Ggml org Ggml Vision Model Inference
- Workflow:Axolotl ai cloud Axolotl QLoRA SFT Finetuning
- Workflow:PrefectHQ Prefect AI Data Analyst Agent
- Workflow:Huggingface Alignment handbook ORPO Single Stage Alignment
- Workflow:Roboflow Rf detr Roboflow Deployment
- Workflow:BerriAI Litellm SDK Completion
- Workflow:Langchain ai Langgraph ReAct Agent Creation
- Workflow:Langgenius Dify Workflow Builder and Execution
- Workflow:Openai Openai agents python Tool Integrated Agent
- Workflow:Sdv dev SDV Multi table synthesis
Principles
- Principle:Cohere ai Cohere python Embed Response Processing
- Principle:SeleniumHQ Selenium CDP Event Subscription
- Principle:Huggingface Open r1 GRPO Training
- Principle:NVIDIA NeMo Curator Image Ingestion
- Principle:Onnx Onnx Model Inspection
- Principle:EvolvingLMMs Lab Lmms eval SGLang Acceleration
- Principle:Huggingface Diffusers Video Pipeline Selection
- Principle:Gretelai Gretel synthetics Batch Synthetic Generation
- Principle:Teamcapybara Capybara Page Navigation
- Principle:Spotify Luigi Web Visualiser Monitoring
Implementations
- Implementation:PacktPublishing LLM Engineers Handbook Create Train Test Split
- Implementation:Confident ai Deepeval ContextGenerator
- Implementation:Facebookresearch Habitat lab Hitl main
- Implementation:Openai Openai python Response Refusal Done
- Implementation:ArroyoSystems Arroyo Table Manager Checkpoint
- Implementation:Langchain ai Langchain ChatMistralAI
- Implementation:Marker Inc Korea AutoRAG CohereReranker
- Implementation:OWASP Www project top 10 for large language model applications ResultsAnalyzer Compile Report
- Implementation:Triton inference server Server GenQaSequenceModels
- Implementation:Online ml River Base DriftDetector
Heuristics
- Heuristic:Apache Shardingsphere DDL Refresher Superclass Fallback
- Heuristic:Datahub project Datahub Batch Size And Timeout Tuning
- Heuristic:Infiniflow Ragflow Hybrid Search Fallback Strategy
- Heuristic:Nautechsystems Nautilus trader Inflight Order Check Threshold
- Heuristic:Sdv dev SDV CTGAN Column Performance
- Heuristic:Alibaba MNN GPU Tuning Modes
- Heuristic:Allenai Open instruct GPU Memory Utilization
- Heuristic:Apache Dolphinscheduler Gzip Compression Threshold
- Heuristic:Puppeteer Puppeteer Navigation Race Condition Avoidance
- Heuristic:Deepspeedai DeepSpeed Sequence Parallel PyTorch Version
Environments
- Environment:Intel Ipex llm XPU Finetuning Environment
- Environment:Triton inference server Server Docker Container Build
- Environment:Confident ai Deepeval LLM Provider Credentials
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:Huggingface Trl PEFT LoRA Environment
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:Heibaiying BigData Notes Hadoop CDH Environment
- Environment:Sail sg LongSpec Inference Environment
- Environment:AnswerDotAI RAGatouille GPU CUDA Runtime
- Environment:Apache Kafka Docker Build Environment