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:Huggingface Trl Direct Preference Optimization
- Workflow:Isaac sim IsaacGymEnvs RL Policy Training
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:CrewAIInc CrewAI Crew Training And Testing
- Workflow:Diagram of thought Diagram of thought DoT Prompt Customization
- Workflow:Predibase Lorax Multi Adapter Merging
- Workflow:Ucbepic Docetl Playground Interactive Development
- Workflow:Datahub project Datahub Docker Quickstart Deployment
- Workflow:Truera Trulens RAG With Guardrails
- Workflow:Protectai Llm guard API Server Deployment
Principles
- Principle:Triton inference server Server Inference Request
- Principle:Webdriverio Webdriverio CLI Architecture
- Principle:Openclaw Openclaw Version Update
- Principle:Eventual Inc Daft Column Input Normalization
- Principle:Fede1024 Rust rdkafka Custom Client Context
- Principle:Haosulab ManiSkill Imitation Policy Training
- Principle:Heibaiying BigData Notes Kafka Message Polling
- Principle:Huggingface Datatrove Lambda Filtering
- Principle:Haotian liu LLaVA Multimodal Response Generation
- Principle:Evidentlyai Evidently Classification Quality Evaluation
Implementations
- Implementation:Google deepmind Mujoco Engine Collision Primitive
- Implementation:Fede1024 Rust rdkafka ClientConfig Builder
- Implementation:Treeverse LakeFS Java SDK Model CredentialsWithSecret
- Implementation:Triton inference server Server L0 Long Running Stress
- Implementation:Datajuicer Data juicer ReplaceContentMapper
- Implementation:Microsoft Playwright ProcessLauncher
- Implementation:Mlflow Mlflow GraphQL Schema Autogeneration
- Implementation:Langchain ai Langgraph Runtime Class
- Implementation:Vibrantlabsai Ragas MetricBasePrompt
- Implementation:Ollama Ollama Llama Server
Heuristics
- Heuristic:Huggingface Trl Gradient Checkpointing Use Reentrant
- Heuristic:Explodinggradients Ragas Retry And Backoff Configuration
- Heuristic:MarketSquare Robotframework browser Windows Shell NPM Workaround
- Heuristic:Wandb Weave Concurrency Deadlock Prevention
- Heuristic:Cohere ai Cohere python Warning Deprecated Legacy Generate API
- Heuristic:Datahub project Datahub Venv Copies Mode
- Heuristic:Protectai Llm guard ONNX Runtime Optimization
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
- Heuristic:Microsoft BIPIA Delta Weight CPU Loading
- Heuristic:Mlc ai Web llm Service Worker Keep Alive
Environments
- Environment:CarperAI Trlx Python Accelerate
- Environment:Openai Openai agents python OpenAI API Credentials
- Environment:Bitsandbytes foundation Bitsandbytes ROCm AMD Environment
- Environment:Obss Sahi Python Image Processing
- Environment:Helicone Helicone Python ClickHouse Migrations
- Environment:Bentoml BentoML Triton Inference Server
- Environment:NVIDIA TransformerEngine CUDA Toolkit Requirements
- Environment:Sgl project Sglang Prometheus
- Environment:Sgl project Sglang Python Dependencies
- Environment:Huggingface Peft GPU Hardware Detection