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:Openai Openai agents python Guardrails Secured Agent
- Workflow:Dotnet Machinelearning AutoML Experiment
- Workflow:Huggingface Datatrove Dataset Tokenization
- Workflow:Lance format Lance Full Text Search
- Workflow:Microsoft DeepSpeedExamples SuperOffload Finetuning
- Workflow:CarperAI Trlx RLHF Dialogue Alignment
- Workflow:Anthropics Anthropic sdk python Basic Message Conversation
- Workflow:OpenHands OpenHands Organization Onboarding
- Workflow:Ollama Ollama Model Registry Operations
- Workflow:Snorkel team Snorkel Data Augmentation
Principles
- Principle:Kserve Kserve Multi Model Prediction
- Principle:FMInference FlexLLMGen Inference Module Replacement
- Principle:Microsoft Semantic kernel Process Builder Creation
- Principle:HKUDS AI Trader Frontend Configuration Loading
- Principle:Pytorch Serve LLM Text Generation
- Principle:LaurentMazare Tch rs Vocabulary Management
- Principle:Mlfoundations Open flamingo Evaluation Model Abstraction
- Principle:Apache Spark Source Compilation
- Principle:Truera Trulens Server Side Evaluation
- Principle:DataTalksClub Data engineering zoomcamp Dbt Staging Layer
Implementations
- Implementation:CARLA simulator Carla MeshReconstruction
- Implementation:BerriAI Litellm Check Batch Cost
- Implementation:Elevenlabs Elevenlabs python HistoryClient
- Implementation:Sktime Pytorch forecasting NBeats From Dataset
- Implementation:Puppeteer Puppeteer Injected PQuerySelector
- Implementation:Testtimescaling Testtimescaling github io Welcome Branch Setup
- Implementation:Astronomer Astronomer cosmos ClickhouseUserPasswordProfileMapping
- Implementation:NVIDIA NeMo Curator TransNetV2ClipExtractionStage
- Implementation:Datajuicer Data juicer PythonLambdaMapper
- Implementation:AUTOMATIC1111 Stable diffusion webui Extra Options Section
Heuristics
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
- Heuristic:ARISE Initiative Robosuite Numba BSOD Workaround
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Identity Loss Color Preservation
- Heuristic:Huggingface Optimum Dummy Input Shape Defaults
- Heuristic:Apache Druid Query Error Suggestion Patterns
- Heuristic:Getgauge Taiko Navigation Wait Strategy
- Heuristic:Apache Shardingsphere Shadow Routing Hint First Fallback
- Heuristic:Apache Dolphinscheduler Datasource Cache Expiry
- Heuristic:Guardrails ai Guardrails RAIL Argument Parsing Security
- Heuristic:PacktPublishing LLM Engineers Handbook LoRA Finetuning Parameters
Environments
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Apache Airflow Database Backend Environment
- Environment:Volcengine Verl SGLang Rollout Environment
- Environment:Pola rs Polars Cloud Storage Environment
- Environment:Risingwavelabs Risingwave Dashboard Node Environment
- Environment:Microsoft Agent framework Core Package Dependencies
- Environment:Openai Openai node Node 20 Runtime
- Environment:Shiyu coder Kronos HuggingFace Hub Access
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment