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:FlowiseAI Flowise Agentflow V2 Creation
- Workflow:Helicone Helicone Local Development Setup
- Workflow:Iterative Dvc Data Tracking
- Workflow:Promptfoo Promptfoo Red Team Security Scan
- Workflow:Openai Openai python Chat Completion
- Workflow:LaurentMazare Tch rs LLM Text Generation
- Workflow:Sktime Pytorch forecasting TFT Demand Forecasting
- Workflow:Predibase Lorax Server Deployment
- Workflow:Huggingface Transformers PEFT Adapter Integration
- Workflow:PrefectHQ Prefect Web Scraping Pipeline
Principles
- Principle:Google deepmind Mujoco MJX Data Retrieval
- Principle:Open compass VLMEvalKit MCQ Prompt Construction
- Principle:Pytorch Serve Text Classification
- Principle:ArroyoSystems Arroyo Two Phase Commit
- Principle:DistrictDataLabs Yellowbrick Feature Dropping Analysis
- Principle:Zai org CogVideo Frame Interpolation
- Principle:Deepset ai Haystack Document Writing
- Principle:Tensorflow Serving Canary Deployment
- Principle:Zai org CogVideo Video Export
- Principle:Openai Whisper Full Transcription
Implementations
- Implementation:Mlc ai Mlc llm Package
- Implementation:Infiniflow Ragflow McpServerService
- Implementation:Googleapis Python genai Models Edit Image
- Implementation:Ggml org Llama cpp Server Main
- Implementation:Pyro ppl Pyro MiniPyro Example
- Implementation:Openai Evals SolverToolsConvo Runner
- Implementation:ArroyoSystems Arroyo Pipeline Config Modal
- Implementation:Lance format Lance LqCli
- Implementation:Triton inference server Server L0 Metrics Test
- Implementation:Run llama Llama index FunctionCallingLLM
Heuristics
- Heuristic:Protectai Llm guard ONNX Runtime Optimization
- Heuristic:Puppeteer Puppeteer Headless Linux Requirements
- Heuristic:ChenghaoMou Text dedup Bloom Filter Single Process
- Heuristic:Zai org CogVideo Training Hyperparameter Defaults
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:Langgenius Dify SQL Escape Backslash First
- Heuristic:Ray project Ray NaN Score Filtering In PBT
- Heuristic:Openai Openai agents python Default Max Turns Safety Limit
- Heuristic:Openai Whisper Median Word Duration Clamping
- Heuristic:Openclaw Openclaw Warning Suppression For Known Deprecations
Environments
- Environment:Run llama Llama index Fsspec Remote Storage
- Environment:Bitsandbytes foundation Bitsandbytes HPU Gaudi Runtime
- Environment:Mit han lab Llm awq VILA Multimodal Environment
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Guardrails ai Guardrails Docker Server Runtime
- Environment:Cleanlab Cleanlab Python Core Environment
- Environment:NVIDIA TransformerEngine CUDA Toolkit Requirements
- Environment:Farama Foundation Gymnasium Video Recording Dependencies
- Environment:Huggingface Datasets Image Dependencies
- Environment:LMCache LMCache CUDA GPU Runtime