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:Vllm project Vllm Multi LoRA Serving
- Workflow:Openai Openai node Structured Output Parsing
- Workflow:Apache Shardingsphere Cluster Mode Initialization
- Workflow:Microsoft Agent framework Basic Agent Creation
- Workflow:Kubeflow Pipelines Iterative Model Training
- Workflow:PrefectHQ Prefect Database Cleanup With Approval
- Workflow:Lance format Lance Vector Search Pipeline
- Workflow:Fede1024 Rust rdkafka Produce Consume Roundtrip
- Workflow:Apache Spark Building and Testing
- Workflow:Fastai Fastbook Neural Network From Scratch
Principles
- Principle:AUTOMATIC1111 Stable diffusion webui File And Path Utility Functions
- Principle:Zai org CogVideo Video Reconstruction Loss
- Principle:Triton inference server Server Jetson Edge Deployment
- Principle:Langchain ai Langchain Conversation Looping
- Principle:Sdv dev SDV Multi Table Model Fitting
- Principle:Openai Openai python Image Result Processing
- Principle:OpenRLHF OpenRLHF Unpaired Preference Dataset Construction
- Principle:Puppeteer Puppeteer Page Creation
- Principle:Mlflow Mlflow Model Version Management
- Principle:Alibaba ROLL Model Checkpointing
Implementations
- Implementation:Mlc ai Web llm Multi Model RAG Engine
- Implementation:Microsoft Playwright WebKit Protocol Types
- Implementation:Lance format Lance LogicalExpr
- Implementation:Apache Airflow Configuration Parser
- Implementation:Open compass VLMEvalKit WeMath Utils
- Implementation:Triton inference server Server OrcaHTTP
- Implementation:DataTalksClub Data engineering zoomcamp Dlt Resource Decorator
- Implementation:Online ml River Bandit RandomPolicy
- Implementation:Recommenders team Recommenders Sequential Iterator
- Implementation:ClickHouse ClickHouse Clickhouse Client Interactive
Heuristics
- Heuristic:OpenRLHF OpenRLHF Packing Samples Efficiency Tip
- Heuristic:Langchain ai Langchain Warning Deprecated AnthropicLLM
- Heuristic:Scikit learn Scikit learn Data Leakage Prevention
- Heuristic:Microsoft Agent framework PowerFx Python Version Limit
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:Datahub project Datahub Gradle Task Only
- Heuristic:OpenRLHF OpenRLHF Off Policy IS Correction Tip
- Heuristic:Huggingface Alignment handbook DDP Bias Buffer Ignore
- Heuristic:Neuml Txtai Batch Size And Sorting Tip
- Heuristic:Scikit learn Scikit learn Working Memory Tuning
Environments
- Environment:Intel Ipex llm Pipeline Parallel Environment
- Environment:Open compass VLMEvalKit GPU CUDA Environment
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:Mistralai Client python Agents Environment
- Environment:Sail sg LongSpec Inference Environment
- Environment:Langgenius Dify Redis And Celery Environment
- Environment:Treeverse LakeFS Web UI Environment
- Environment:Puppeteer Puppeteer Configuration Environment Variables
- Environment:Mlflow Mlflow OpenAI LLM Integration Environment
- Environment:Mit han lab Llm awq Flash Attention Environment