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:Bigscience workshop Petals Prompt Tuning Classification
- Workflow:DataExpert io Data engineer handbook Dimensional Data Modeling Environment Setup
- Workflow:Cohere ai Cohere python Text Embedding
- Workflow:Infiniflow Ragflow Search Application Setup
- Workflow:OWASP Www project top 10 for large language model applications GenAI Red Team Testing
- Workflow:Ray project Ray Cross Language Invocation
- Workflow:Bitsandbytes foundation Bitsandbytes 8bit Optimizer Training
- Workflow:Evidentlyai Evidently Data Drift Monitoring
- Workflow:Microsoft DeepSpeedExamples SuperOffload Finetuning
- Workflow:Mlfoundations Open flamingo Distributed Training
Principles
- Principle:Ray project Ray Actor Method Invocation
- Principle:Pola rs Polars Python Binding Configuration
- Principle:NVIDIA NeMo Aligner KTO Training
- Principle:Groq Groq python Binary Response Handling
- Principle:Pyro ppl Pyro SMC Filtering Pattern
- Principle:EvolvingLMMs Lab Lmms eval Distributed Environment Setup
- Principle:Triton inference server Server Performance Analysis
- Principle:TA Lib Ta lib python Python Extension Building
- Principle:Haotian liu LLaVA Weight Delta Application
- Principle:Facebookresearch Audiocraft Audio Token Decoding
Implementations
- Implementation:Deepspeedai DeepSpeed XPU Adam Header
- Implementation:Heibaiying BigData Notes HBaseUtils Read Operations
- Implementation:Online ml River Tree Splitter Exhaustive
- Implementation:DevExpress Testcafe StackCleaningHook
- Implementation:SeleniumHQ Selenium JavascriptExecutor
- Implementation:Ucbepic Docetl Directive AgentUtils
- Implementation:Ggml org Llama cpp Diffusion CLI
- Implementation:Nightwatchjs Nightwatch Cucumber Package Install
- Implementation:Openclaw Openclaw RunCli
- Implementation:ClickHouse ClickHouse BorrowedObjectPool
Heuristics
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:Lance format Lance Warning Deprecated Java APIs
- Heuristic:DevExpress Testcafe Browser Connection Timeouts
- Heuristic:Apache Kafka Unknown Record Type Upgrade Safety
- Heuristic:Ray project Ray Graceful Shutdown Timing
- Heuristic:Iterative Dvc YAML Dual Parser Strategy
- Heuristic:Sdv dev SDV Version Compatibility
- Heuristic:Cohere ai Cohere python Embed Auto Batching Strategy
- Heuristic:SeleniumHQ Selenium Warning Deprecated HasDownloads GetDownloadableFiles
- Heuristic:Haotian liu LLaVA Flash Attention GPU Requirement
Environments
- Environment:Microsoft Autogen Studio Server Environment
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:ChenghaoMou Text dedup Python 3 12 Environment
- Environment:MarketSquare Robotframework browser Docker Container
- Environment:Neuml Txtai Docker Deployment Environment
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:Spcl Graph of thoughts OpenAI API Access
- Environment:Allenai Open instruct Ray Distributed
- Environment:Huggingface Alignment handbook Evaluation Tools
- Environment:Getgauge Taiko Node Runtime