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:Mage ai Mage ai Building a New Source Connector
- Workflow:Alibaba ROLL Supervised Finetuning Pipeline
- Workflow:Danijar Dreamerv3 Evaluation Only
- Workflow:Vllm project Vllm OpenAI Compatible Serving
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:Apache Beam Portable Pipeline Submission
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:Confident ai Deepeval AI Agent Evaluation
- Workflow:Heibaiying BigData Notes Storm Topology Development
- Workflow:Langfuse Langfuse Dataset experiment pipeline
Principles
- Principle:Teamcapybara Capybara RSpec Integration
- Principle:Apache Hudi Streaming Write Execution
- Principle:Ollama Ollama MultimodalPipeline
- Principle:Recommenders team Recommenders Benchmark Results Compilation
- Principle:Facebookresearch Audiocraft Finetuning Checkpoint Preparation
- Principle:Langgenius Dify Volume Initialization
- Principle:Facebookresearch Audiocraft Encoder Decoder Architecture
- Principle:OpenGVLab InternVL Benchmark Dispatch
- Principle:Google deepmind Dm control Domain Randomization
- Principle:EvolvingLMMs Lab Lmms eval TUI Server Architecture
Implementations
- Implementation:DevExpress Testcafe RequestHook
- Implementation:ArroyoSystems Arroyo Schema Provider
- Implementation:Guardrails ai Guardrails DocumentStore
- Implementation:Alibaba ROLL RewardFL ActorWorker Train Step
- Implementation:Avhz RustQuant Descriptive Statistics
- Implementation:Microsoft Autogen Studio Sidebar
- Implementation:Cypress io Cypress Mount Stub
- Implementation:AUTOMATIC1111 Stable diffusion webui Save image
- Implementation:Eventual Inc Daft Session Write Table
- Implementation:Deepspeedai DeepSpeed DeepSpeedEngine Save For RLHF
Heuristics
- Heuristic:Langchain ai Langgraph Durability Mode Selection
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
- Heuristic:Fastai Fastbook Progressive Resizing
- Heuristic:Apache Paimon Vector Index Configuration Tips
- Heuristic:Vibrantlabsai Ragas Temperature Sampling Strategy
- Heuristic:Microsoft Autogen Graph Validation Rules
- Heuristic:Openai Openai agents python Sensitive Data Logging Defaults
- Heuristic:Bigscience workshop Petals KV Cache Sizing For Attention Types
- Heuristic:LLMBook zh LLMBook zh github io LoRA Initialization Strategy
- Heuristic:Ggml org Llama cpp Thread Count Tuning
Environments
- Environment:Unstructured IO Unstructured PDF Dependencies
- Environment:LMCache LMCache Python Runtime
- Environment:Huggingface Datasets Audio Video Dependencies
- Environment:Scikit learn contrib Imbalanced learn Keras TensorFlow
- Environment:Huggingface Transformers Flash Attention 2 Env
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Risingwavelabs Risingwave Java Connector Environment
- Environment:Heibaiying BigData Notes Java 8 Maven Environment
- Environment:Lm sys FastChat GPU CUDA Inference