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:Hpcaitech ColossalAI RAG Application
- Workflow:Nautechsystems Nautilus trader Live trading deployment
- Workflow:Mlc ai Web llm Basic Chat Completion
- Workflow:LMCache LMCache CacheBlend KV Reuse
- Workflow:Intel Ipex llm RAG With LangChain
- Workflow:Ggml org Llama cpp Text Generation
- Workflow:Datahub project Datahub Docker Quickstart Deployment
- Workflow:Alibaba ROLL Agentic RL Training Pipeline
- Workflow:Apache Shardingsphere Metadata DDL Refresh
- Workflow:Openclaw Openclaw Docker Deployment
Principles
- Principle:Openclaw Openclaw Channel Registration
- Principle:Langgenius Dify Node Graph Composition
- Principle:CarperAI Trlx RL Data Structures
- Principle:FlowiseAI Flowise Vector Store Provider Configuration
- Principle:ContextualAI HALOs Model Checkpointing
- Principle:InternLM Lmdeploy Multimodal Inference
- Principle:Vespa engine Vespa Subscriber Shutdown
- Principle:SqueezeAILab ETS Policy Model Serving
- Principle:Huggingface Peft Adapter Persistence
- Principle:CarperAI Trlx Prompt Preparation
Implementations
- Implementation:Iamhankai Forest of Thought ToT Task Run
- Implementation:Allenai Open instruct FlatArguments
- Implementation:Treeverse LakeFS Java SDK Model SetupState
- Implementation:Lance format Lance TakeBench
- Implementation:Anthropics Anthropic sdk python Beta Tool Decorator
- Implementation:Google deepmind Dm control Composer Environment For Manipulation
- Implementation:Langgenius Dify FetchAllInspectVars
- Implementation:Vibrantlabsai Ragas AgUI Integration
- Implementation:Microsoft Playwright Validator Primitives
- Implementation:Mlc ai Web llm Package Configuration
Heuristics
- Heuristic:Langgenius Dify SSE Streaming Error Handling
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:LLMBook zh LLMBook zh github io Greedy Decoding Temperature Zero
- Heuristic:OpenGVLab InternVL Packed Training Buffer Management
- Heuristic:Openai Openai python Streaming Resource Management
- Heuristic:PacktPublishing LLM Engineers Handbook Token Window Safety Margin
- Heuristic:Hpcaitech ColossalAI Flash Attention Dtype Restriction
- Heuristic:Mlc ai Mlc llm BLAS Dispatch Decision
- Heuristic:Huggingface Datasets Num Proc Guidelines
- Heuristic:Vespa engine Vespa Document Batch Processing Strategy
Environments
- Environment:Ollama Ollama CGo Runtime
- Environment:Unstructured IO Unstructured All Docs
- Environment:Kserve Kserve SRIOV RDMA Network
- Environment:Intel Ipex llm XPU Inference Environment
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:CarperAI Trlx Python Accelerate
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:Langfuse Langfuse Docker Infrastructure
- Environment:ChenghaoMou Text dedup Suffix Array External Tools
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention