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:Haifengl Smile Model Serving Pipeline
- Workflow:Sgl project Sglang Structured Output Generation
- Workflow:ARISE Initiative Robomimic Trained Policy Evaluation
- Workflow:Vibrantlabsai Ragas Experiment Driven Development
- Workflow:Truera Trulens RAG Evaluation With LangChain
- Workflow:Turboderp org Exllamav2 Text Generation
- Workflow:Ollama Ollama OpenAI API Compatibility
- Workflow:Online ml River Online Clustering
- Workflow:Microsoft Agent framework Multi Agent Concurrent Orchestration
- Workflow:Apache Spark Building and Testing
Principles
- Principle:Ollama Ollama Token Sampling
- Principle:ARISE Initiative Robosuite Gripper Testing
- Principle:Arize ai Phoenix Prompt Retrieval
- Principle:Iterative Dvc Local Remote State Comparison
- Principle:Ucbepic Docetl Chunk Result Reduction
- Principle:Protectai Modelscan Issue Severity Classification
- Principle:Nautechsystems Nautilus trader Portfolio Analysis
- Principle:Googleapis Python genai Response Processing
- Principle:FMInference FlexLLMGen Model Weight Downloading
- Principle:Mlfoundations Open flamingo Benchmark Dataset Loading
Implementations
- Implementation:NVIDIA NeMo Aligner Anneal SDXL
- Implementation:Avhz RustQuant Interpolator Trait
- Implementation:Microsoft Playwright BidiPdf
- Implementation:Nautechsystems Nautilus trader BacktestEngine Add Venue
- Implementation:CrewAIInc CrewAI Serply News Search Tool
- Implementation:FlowiseAI Flowise CreateDocumentStore
- Implementation:Mage ai Mage ai GitHub Issue Events Schema
- Implementation:NVIDIA DALI YOLOv4 Model
- Implementation:Tensorflow Tfjs GraphModel Predict
- Implementation:NVIDIA DALI TensorShape Tests
Heuristics
- Heuristic:Bitsandbytes foundation Bitsandbytes Compute Dtype Mismatch Warning
- Heuristic:Puppeteer Puppeteer Firefox Single Process Workaround
- Heuristic:Danijar Dreamerv3 XLA GPU Optimization Flags
- Heuristic:ClickHouse ClickHouse Debug Build Tips
- Heuristic:Openclaw Openclaw Warning Suppression For Known Deprecations
- Heuristic:Zai org CogVideo BF16 FP16 Precision Selection
- Heuristic:Explodinggradients Ragas LLM Temperature Defaults
- Heuristic:Mage ai Mage ai Parallel Sink Concurrency Limit
- Heuristic:Haotian liu LLaVA Tokenizer Version Offset Correction
- Heuristic:Google deepmind Dm control Physics Timestep Configuration
Environments
- Environment:Princeton nlp Tree of thought llm Python OpenAI
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:DataExpert io Data engineer handbook PostgreSQL Docker Environment
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:Datajuicer Data juicer Python Runtime Environment
- Environment:Rapidsai Cuml CUDA GPU
- Environment:Sgl project Sglang Kubernetes
- Environment:Openclaw Openclaw Docker Deployment Environment
- Environment:Mlc ai Mlc llm CUDA GPU Environment
- Environment:OpenBMB UltraFeedback HuggingFace Hub Environment