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:Webdriverio Webdriverio Standalone Browser Automation
- Workflow:Alibaba MNN Python Model Inference
- Workflow:Interpretml Interpret Model Explanation And Visualization
- Workflow:Marker Inc Korea AutoRAG Evaluation Data Creation
- Workflow:Sail sg LongSpec GLIDE Draft Model Training
- Workflow:Tensorflow Serving Batched Inference Pipeline
- Workflow:ThreeSR Awesome Inference Time Scaling Automated Paper Addition
- Workflow:Langgenius Dify App Creation and Configuration
- Workflow:Recommenders team Recommenders Algorithm Benchmarking
- Workflow:Zai org CogVideo Diffusers Image to Video Inference
Principles
- Principle:Haotian liu LLaVA LoRA Training
- Principle:Tensorflow Serving Dependency Ownership
- Principle:BerriAI Litellm Cache Initialization
- Principle:SeleniumHQ Selenium Page Object Annotation
- Principle:Huggingface Datatrove HTTP Media Fetching
- Principle:Open compass VLMEvalKit Parallel Task Execution
- Principle:PacktPublishing LLM Engineers Handbook Prompt Engineering For Dataset Generation
- Principle:Lucidrains X transformers Preference Data Preparation
- Principle:OpenGVLab InternVL LoRA Adapter Merging
- Principle:Heibaiying BigData Notes Kafka Rebalancing and Shutdown
Implementations
- Implementation:BerriAI Litellm Audit Logging Endpoints
- Implementation:InternLM Lmdeploy Impl 1688
- Implementation:Unstructured IO Unstructured ChunkingOptions
- Implementation:Apache Flink FatalExceptionClassifier IsFatal
- Implementation:Apache Druid Partition Config Form
- Implementation:DataTalksClub Data engineering zoomcamp Dbt Staging Models
- Implementation:Mlc ai Mlc llm Metrics Header
- Implementation:Ollama Ollama Template Index
- Implementation:Ggml org Llama cpp Save Load State
- Implementation:Dotnet Machinelearning LdaHybridAliasMap
Heuristics
- Heuristic:HKUDS AI Trader Sortino Ratio Capping
- Heuristic:Guardrails ai Guardrails RAIL Argument Parsing Security
- Heuristic:OWASP Www project top 10 for large language model applications Warning Deprecated Markdown To PDF Convert
- Heuristic:Microsoft Agent framework Declaration Only Tools Pattern
- Heuristic:Mbzuai oryx Awesome LLM Post training Excel Sheet Name Truncation
- Heuristic:Apache Kafka JVM GC Tuning Defaults
- Heuristic:PacktPublishing LLM Engineers Handbook Dataset Generation Quality Filters
- Heuristic:Datajuicer Data juicer Partition Size Tuning
- Heuristic:Langchain ai Langchain Deprecation Version Tracking
- Heuristic:Princeton nlp Tree of thought llm Value Caching
Environments
- Environment:PacktPublishing LLM Engineers Handbook Docker MongoDB Qdrant Infrastructure
- Environment:Huggingface Trl DeepSpeed Environment
- Environment:DataTalksClub Data engineering zoomcamp Kestra Orchestration Environment
- Environment:Pola rs Polars Cloud Storage Environment
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Mbzuai oryx Awesome LLM Post training Python Matplotlib
- Environment:Sgl project Sglang CUDA Runtime
- Environment:InternLM Lmdeploy Build From Source
- Environment:Vllm project Vllm NVIDIA CUDA
- Environment:Hiyouga LLaMA Factory FP8 Training Environment