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:OWASP Www project top 10 for large language model applications Vulnerability Entry Development
- Workflow:Langchain ai Langgraph Functional API Workflow
- Workflow:Eventual Inc Daft SQL Query Analytics
- Workflow:Apache Paimon Blob Storage With Descriptors
- Workflow:Recommenders team Recommenders SAR Collaborative Filtering
- Workflow:Microsoft Autogen Studio Team Deployment
- Workflow:Cleanlab Cleanlab Token Classification Label Quality
- Workflow:Promptfoo Promptfoo Project Initialization
- Workflow:Anthropics Anthropic sdk python Tool Use Integration
- Workflow:Puppeteer Puppeteer Web Scraping And Interaction
Principles
- Principle:Mistralai Client python File Upload
- Principle:Pola rs Polars Expression Pipeline Building
- Principle:Kubeflow Kubeflow Post Deployment Verification
- Principle:Snorkel team Snorkel Label Quality Evaluation
- Principle:Intel Ipex llm Offline Batch Inference
- Principle:Huggingface Transformers Device Mesh Topology
- Principle:Haifengl Smile Model Discovery
- Principle:Deepset ai Haystack Evaluation Result Reporting
- Principle:Triton inference server Server Container Verification
- Principle:FlowiseAI Flowise Execution Monitoring
Implementations
- Implementation:Promptfoo Promptfoo Sidebars Config
- Implementation:TobikoData Sqlmesh Button
- Implementation:Ggml org Llama cpp Mtmd Helper
- Implementation:Ollama Ollama Thinking Template
- Implementation:Ucbepic Docetl PromptImprovementDialog
- Implementation:ArroyoSystems Arroyo Datastream Optimizers
- Implementation:Huggingface Datatrove ParquetWriter
- Implementation:Haosulab ManiSkill ReplicaCADRearrangeSceneBuilder
- Implementation:Mage ai Mage ai Destination Process Record
- Implementation:ChenghaoMou Text dedup SimHash Get Embed Func
Heuristics
- Heuristic:Obss Sahi Overlap Ratio Selection
- Heuristic:NVIDIA DALI Batch Size Tuning
- Heuristic:Openai Evals Event Batching Configuration
- Heuristic:Helicone Helicone Provider URL Regex Priority
- Heuristic:Ggml org Ggml Quantization Type Selection
- Heuristic:Astronomer Astronomer cosmos Dbt Invocation Mode Selection
- Heuristic:Eric mitchell Direct preference optimization RMSprop Over Adam
- Heuristic:OpenBMB UltraFeedback Score 10 Anomaly Correction
- Heuristic:Dagster io Dagster Batch Size Tuning
- Heuristic:Hpcaitech ColossalAI Warning Deprecated Ray Detached PPO
Environments
- Environment:Zai org CogVideo Video Captioning Environment
- Environment:FMInference FlexLLMGen NVMe Disk
- Environment:Scikit learn contrib Imbalanced learn Python Scikit learn
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:Huggingface Datatrove Slurm Cluster Environment
- Environment:Apache Airflow Docker Container Environment
- Environment:Apache Spark JDK Build Environment
- Environment:BerriAI Litellm Provider API Credentials
- Environment:Huggingface Datatrove Inference GPU Environment
- Environment:Unstructured IO Unstructured Profiling Tools