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:VainF Torch Pruning LLM Structural Pruning
- Workflow:Haotian liu LLaVA Web Demo Deployment
- Workflow:Mlflow Mlflow Experiment Tracking
- Workflow:Iamhankai Forest of Thought Game24 Forest Solving
- Workflow:SqueezeAILab ETS ETS Experiment Pipeline
- Workflow:Microsoft Semantic kernel Agent Conversation And Orchestration
- Workflow:Sgl project Sglang Multimodal Vision Language Inference
- Workflow:Ollama Ollama Model Registry Operations
- Workflow:Avhz RustQuant Model Calibration
- Workflow:Ggml org Llama cpp Speculative Decoding
Principles
- Principle:Huggingface Optimum Task and Model Resolution
- Principle:Ollama Ollama CLI Format Utility
- Principle:TA Lib Ta lib python Abstract Function Execution
- Principle:LaurentMazare Tch rs Top K Prediction
- Principle:Google deepmind Mujoco MJX Data Retrieval
- Principle:LaurentMazare Tch rs LLM Weight Conversion
- Principle:Webdriverio Webdriverio Gherkin Feature Specification
- Principle:Lm sys FastChat Leaderboard Dashboard Rendering
- Principle:Ucbepic Docetl Chunk Result Reduction
- Principle:OpenGVLab InternVL Streamlit Chat Interface
Implementations
- Implementation:Turboderp org Exllamav2 ThreadPool
- Implementation:Arize ai Phoenix Traces Resource
- Implementation:ClickHouse ClickHouse BFloat16
- Implementation:Facebookresearch Audiocraft Audio write
- Implementation:Apache Spark SparkLauncher
- Implementation:Hiyouga LLaMA Factory V1 Arg Utils
- Implementation:Datahub project Datahub Container Entity
- Implementation:Openai Openai agents python RunResult
- Implementation:Neuml Txtai HTMLToMarkdown
- Implementation:Tensorflow Serving Gzip Zlib Test
Heuristics
- Heuristic:Apache Airflow Variable Access Pattern
- Heuristic:ARISE Initiative Robosuite Observation Key Selection
- Heuristic:Sdv dev SDV HMA Schema Simplification
- Heuristic:Avdvg InjectGuard Sim K Threshold Tuning
- Heuristic:Mlfoundations Open flamingo RICES Feature Caching
- Heuristic:PeterL1n BackgroundMattingV2 Checkpoint Interval Tuning
- Heuristic:HKUDS AI Trader Sortino Ratio Capping
- Heuristic:Deepset ai Haystack Pipeline Max Runs Safety Limit
- Heuristic:Onnx Onnx Opset Version Selection
- Heuristic:HKUDS AI Trader A Share Lot Size Rule
Environments
- Environment:Huggingface Diffusers PyTorch CUDA Runtime
- Environment:Marker Inc Korea AutoRAG Python 3 10 Runtime
- Environment:Spotify Luigi SQLAlchemy Database
- Environment:Evidentlyai Evidently SQL Storage Environment
- Environment:Marker Inc Korea AutoRAG Vector Database Backends
- Environment:Huggingface Datatrove Python Runtime
- Environment:Spotify Luigi Python Runtime
- Environment:Openai Evals OpenAI API Configuration
- Environment:Ucbepic Docetl Python Runtime
- Environment:PacktPublishing LLM Engineers Handbook Docker MongoDB Qdrant Infrastructure