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:Volcengine Verl Data Preprocessing For RL
- Workflow:Apache Shardingsphere Metadata DDL Refresh
- Workflow:Ollama Ollama OpenAI API Compatibility
- Workflow:Run llama Llama index Evaluation Pipeline
- Workflow:Haotian liu LLaVA Benchmark Evaluation
- Workflow:Teamcapybara Capybara Form Testing
- Workflow:Norrrrrrr lyn WAInjectBench Text Prompt Injection Detection
- Workflow:Trailofbits Fickling PyTorch Format Identification
- Workflow:Trailofbits Fickling PyTorch Payload Injection
- Workflow:Facebookresearch Habitat lab Rearrangement HRL Training
Principles
- Principle:Tensorflow Serving Remote Predict Op
- Principle:Microsoft Semantic kernel Prompt With Function Calling
- Principle:Ucbepic Docetl Document Splitting
- Principle:Helicone Helicone Registry Snapshot Testing
- Principle:Openclaw Openclaw Global CLI State Management
- Principle:Huggingface Diffusers Package Distribution
- Principle:Langchain ai Langgraph Channel Types
- Principle:AUTOMATIC1111 Stable diffusion webui Image output saving
- Principle:Google deepmind Mujoco Ray Casting
- Principle:Huggingface Datatrove Dataset Integrity Validation
Implementations
- Implementation:Promptfoo Promptfoo resolveConfigs
- Implementation:Run llama Llama index QueryFusionRetriever
- Implementation:Spotify Luigi Task Dependencies
- Implementation:Open compass VLMEvalKit WorldSense Utils
- Implementation:NVIDIA TransformerEngine Ops Fused Forward Linear Scale Add
- Implementation:Scikit learn Scikit learn Load Iris
- Implementation:Ggml org Llama cpp Json Schema To Grammar Header
- Implementation:DistrictDataLabs Yellowbrick ValidationCurve Visualizer
- Implementation:TobikoData Sqlmesh ColumnLevel Help
- Implementation:NVIDIA TransformerEngine PyTorch Pybind
Heuristics
- Heuristic:Kubeflow Kubeflow Stale Issue Lifecycle Management
- Heuristic:Kserve Kserve Multinode Replica Calculation
- Heuristic:SeldonIO Seldon core Autoscaling Dual Config Tip
- Heuristic:DataTalksClub Data engineering zoomcamp Dbt Materialization Strategy
- Heuristic:Bigscience workshop Petals Prompt Embeddings Float32 Precision
- Heuristic:Neuml Txtai Model Quantization Defaults
- Heuristic:Apache Druid Explore Compare Query Strategy
- Heuristic:Fastai Fastbook Weight Decay Tuning
- Heuristic:Princeton nlp SimPO Hyperparameter Tuning
- Heuristic:Google deepmind Dm control Warning Deprecated Legacy Base Walker
Environments
- Environment:Norrrrrrr lyn WAInjectBench Conda Python 39 CUDA Environment
- Environment:CrewAIInc CrewAI LLM Provider Credentials
- Environment:Apache Flink Python PyFlink Environment
- Environment:Vllm project Vllm ROCm
- Environment:Webdriverio Webdriverio Cloud Service Credentials
- Environment:Langgenius Dify Vector Database Environment
- Environment:Fastai Fastbook Sklearn Environment
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:Helicone Helicone Node 20 TypeScript Runtime