Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Pyro ppl Pyro Discrete Enumeration
- Workflow:Langgenius Dify Knowledge Base Management
- Workflow:Arize ai Phoenix LLM Evaluation Pipeline
- Workflow:Cohere ai Cohere python Chat Completion
- Workflow:Microsoft Onnxruntime Nodejs Inference
- Workflow:AUTOMATIC1111 Stable diffusion webui Text to image generation
- Workflow:ContextualAI HALOs Reward Model Training
- Workflow:Neuml Txtai Agent Execution
- Workflow:Alibaba MNN Python Model Inference
- Workflow:Scikit learn Scikit learn Data Preprocessing Pipeline
Principles
- Principle:LMCache LMCache Engine Configuration
- Principle:AnswerDotAI RAGatouille Model Export
- Principle:Getgauge Taiko Browser Closure
- Principle:Recommenders team Recommenders Chronological Data Splitting
- Principle:Helicone Helicone Mapper Type Detection
- Principle:Online ml River Page Hinkley Drift Detection
- Principle:Scikit learn Scikit learn Column Selection
- Principle:Vllm project Vllm Vllm Installation
- Principle:BerriAI Litellm Callback Registration
- Principle:Microsoft DeepSpeedExamples Baseline PyTorch Training
Implementations
- Implementation:Webdriverio Webdriverio XPath Detection
- Implementation:Mage ai Mage ai Pipedrive Tap
- Implementation:Treeverse LakeFS Java SDK Model ObjectStatsList
- Implementation:Deepseek ai Janus CFG Input Preparation AR
- Implementation:Teamcapybara Capybara Node Element Interaction
- Implementation:Sgl project Sglang Sparse Flash Attention
- Implementation:AUTOMATIC1111 Stable diffusion webui FrozenCLIPEmbedderWithCustomWords forward
- Implementation:Langgenius Dify App Context
- Implementation:TobikoData Sqlmesh FileExplorer Directory
- Implementation:Tensorflow Serving BatchingOptions Configuration
Heuristics
- Heuristic:Ollama Ollama VRAM Recovery And Scheduling
- Heuristic:Huggingface Peft Gradient Checkpointing With Quantization
- Heuristic:ARISE Initiative Robosuite Domain Randomization Tuning
- Heuristic:Unslothai Unsloth Gradient Checkpointing Modes
- Heuristic:Allenai Open instruct Warning Archived Dev Scripts
- Heuristic:Openclaw Openclaw Cache TTL Asymmetric Strategy
- Heuristic:Lm sys FastChat GPU Memory Allocation Strategy
- Heuristic:Zai org CogVideo Decord Import Order Bug
- Heuristic:Infiniflow Ragflow Hybrid Search Fallback Strategy
- Heuristic:Tensorflow Serving Model Warmup Strategy
Environments
- Environment:DistrictDataLabs Yellowbrick Python Scikit Learn Environment
- Environment:Ray project Ray CI Build Matrix Environment
- Environment:Openai Openai agents python MCP Dependencies
- Environment:Datahub project Datahub Docker Quickstart Environment
- Environment:Openai Openai node WebSocket Dependency
- Environment:ContextualAI HALOs CUDA 12 1 Training Environment
- Environment:Lance format Lance SIMD And Platform Requirements
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies
- Environment:Ray project Ray Python Runtime Environment
- Environment:Alibaba ROLL Python Runtime Environment