Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Alibaba ROLL Reward Flow Diffusion Pipeline
- Workflow:Interpretml Interpret EBM Training And Prediction
- Workflow:ArroyoSystems Arroyo Checkpoint Recovery
- Workflow:Marker Inc Korea AutoRAG Evaluation Data Creation
- Workflow:Cypress io Cypress Local Development Environment
- Workflow:Microsoft BIPIA Attack Success Rate Evaluation
- Workflow:Ggml org Llama cpp Interactive Chat
- Workflow:FlowiseAI Flowise Agentflow V2 Creation
- Workflow:Deepspeedai DeepSpeed ZeRO Distributed Training
- Workflow:Langchain ai Langgraph ReAct Agent Creation
Principles
- Principle:Ray project Ray Application Deployment
- Principle:AUTOMATIC1111 Stable diffusion webui High resolution fix
- Principle:NVIDIA NeMo Aligner Hydra Training Configuration
- Principle:Microsoft BIPIA Prompt Construction With Defense
- Principle:Getgauge Taiko File Attachment
- Principle:Getgauge Taiko Network Emulation
- Principle:Facebookresearch Habitat lab HITL Application Configuration
- Principle:Facebookresearch Habitat lab Benchmark Configuration
- Principle:Langchain ai Langgraph UI Component Management
- Principle:Infiniflow Ragflow Parser Options Configuration
Implementations
- Implementation:Openai Openai node ChatKit Threads Resource
- Implementation:Cohere ai Cohere python ApiError
- Implementation:Mage ai Mage ai Commercetools Orders Schema
- Implementation:CARLA simulator Carla Map API Spec
- Implementation:FlowiseAI Flowise SafeHTML
- Implementation:Pola rs Polars Streaming Show Graph
- Implementation:Deepspeedai DeepSpeed Normalize Layer
- Implementation:Microsoft Playwright React CT Mount
- Implementation:Ggml org Llama cpp Conversion Utils
- Implementation:Vespa engine Vespa Docproc ABI Spec
Heuristics
- Heuristic:Bigscience workshop Petals Batch Splitting Threshold
- Heuristic:Unstructured IO Unstructured Libmagic Filetype Accuracy
- Heuristic:Apache Shardingsphere Worker ID Reservation Strategy
- Heuristic:CarperAI Trlx PEFT LoRA Integration
- Heuristic:Cohere ai Cohere python Pydantic V1 V2 Compatibility
- Heuristic:Sktime Pytorch forecasting Gradient Clipping Value
- Heuristic:Apache Kafka Coordinator Loading Commit Interval
- Heuristic:Puppeteer Puppeteer Navigation Race Condition Avoidance
- Heuristic:Webdriverio Webdriverio Exponential Backoff Retry
- Heuristic:PacktPublishing LLM Engineers Handbook LoRA Finetuning Parameters
Environments
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:PacktPublishing LLM Engineers Handbook Unsloth Finetuning Environment
- Environment:Apache Druid Druid Cluster Api
- Environment:Microsoft Agent framework Core Package Dependencies
- Environment:Lm sys FastChat SFT Training Environment
- Environment:Onnx Onnx Python Runtime Environment
- Environment:Farama Foundation Gymnasium JAX Functional Backend
- Environment:Sail sg LongSpec Inference Environment
- Environment:NVIDIA NeMo Curator NVIDIA DALI
- Environment:Eric mitchell Direct preference optimization PyTorch CUDA