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:Nightwatchjs Nightwatch E2E Test Authoring
- Workflow:DataTalksClub Data engineering zoomcamp Spark Batch Processing
- Workflow:Groq Groq python Audio Transcription
- Workflow:Openai Openai agents python Human In The Loop Approval
- Workflow:Teamcapybara Capybara RSpec Integration Setup
- Workflow:Googleapis Python genai Text Content Generation
- Workflow:Explodinggradients Ragas LLM Benchmarking
- Workflow:Haosulab ManiSkill RL Training with PPO
- Workflow:Apache Dolphinscheduler Datasource Connection Management
- Workflow:DataExpert io Data engineer handbook PySpark Job Testing
Principles
- Principle:Evidentlyai Evidently ML Task Configuration
- Principle:DataTalksClub Data engineering zoomcamp Data Deduplication
- Principle:Hpcaitech ColossalAI Distributed Checkpoint Saving
- Principle:Tensorflow Serving Thread Pool Management
- Principle:Testtimescaling Testtimescaling github io Badge Data Generation
- Principle:Alibaba MNN Input Preprocessing
- Principle:Puppeteer Puppeteer Browser Launching
- Principle:Ggml org Llama cpp Model Architecture Registry
- Principle:Sdv dev SDV DayZ Multi Table Parameter Detection
- Principle:Langgenius Dify ErrorHandling
Implementations
- Implementation:ArroyoSystems Arroyo Run Pipeline
- Implementation:Open compass VLMEvalKit RBDash
- Implementation:Neuml Txtai Transcription
- Implementation:Huggingface Datasets Py Utils
- Implementation:Facebookresearch Audiocraft CompressionSolver run step
- Implementation:TA Lib Ta lib python Abstract Function Configuration
- Implementation:Langchain ai Langchain Tool Decorator
- Implementation:BerriAI Litellm CyberArk Secret Manager
- Implementation:Datajuicer Data juicer VideoCameraCalibrationStaticDeepcalibMapper
- Implementation:FlagOpen FlagEmbedding Matryoshka Compensation Data
Heuristics
- Heuristic:Ggml org Llama cpp Quantization Quality Tips
- Heuristic:Kornia Kornia CPU GPU Branching Tip
- Heuristic:Openai Evals Event Batching Configuration
- Heuristic:Infiniflow Ragflow Citation Threshold Decay
- Heuristic:Mlc ai Web llm Grammar Matcher Reuse
- Heuristic:Duckdb Duckdb Memory Management Rules
- Heuristic:AnswerDotAI RAGatouille In Memory Reranking Limits
- Heuristic:Togethercomputer Together python Multipart Upload Strategy
- Heuristic:Lance format Lance IO Buffer And Batch Sizing
- Heuristic:Puppeteer Puppeteer Chrome Default Launch Arguments
Environments
- Environment:TA Lib Ta lib python Python Build Environment
- Environment:OpenBMB UltraFeedback vLLM Multi GPU Environment
- Environment:Ucbepic Docetl Frontend Node Environment
- Environment:Langfuse Langfuse S3 Compatible Storage
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Ucbepic Docetl Python Runtime
- Environment:Google deepmind Dm control OSMesa Software Rendering
- Environment:Microsoft Semantic kernel OpenAI API Environment
- Environment:Intel Ipex llm CPU Finetuning Environment
- Environment:Nautechsystems Nautilus trader Databento API Credentials