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:Microsoft BIPIA Attack Success Rate Evaluation
- Workflow:Promptfoo Promptfoo Project Initialization
- Workflow:Speechbrain Speechbrain Speech Enhancement Training
- Workflow:Ggml org Llama cpp LoRA Adapter Workflow
- Workflow:Mage ai Mage ai API Source Extraction
- Workflow:ARISE Initiative Robosuite Environment Setup And Simulation
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:Scikit learn Scikit learn Ensemble Model Building
- Workflow:MarketSquare Robotframework browser JavaScript Extension
- Workflow:Truera Trulens RAG Evaluation With LangChain
Principles
- Principle:ArroyoSystems Arroyo Pipeline Shutdown
- Principle:OpenBMB UltraFeedback Environment Setup
- Principle:Ggml org Llama cpp Context Extension
- Principle:Ggml org Llama cpp Grammar Constrained Decoding
- Principle:Sgl project Sglang Frontend Backend Initialization
- Principle:OpenGVLab InternVL Dynamic Resolution Preprocessing
- Principle:Pola rs Polars Thread Safe Buffer Management
- Principle:Microsoft Agent framework Agent Construction
- Principle:CARLA simulator Carla Traffic Behavior Configuration
- Principle:Evidentlyai Evidently LLM Judge Evaluation
Implementations
- Implementation:Ggml org Llama cpp Debug Header
- Implementation:Deepseek ai Janus CFG Input Preparation Flow
- Implementation:Online ml River Tree SGT Losses
- Implementation:Vespa engine Vespa FRTConnectionPool Constructor
- Implementation:Ollama Ollama Imagegen Transfer
- Implementation:DataExpert io Data engineer handbook Statsig Get experiment
- Implementation:Hiyouga LLaMA Factory V1 Inference Engine
- Implementation:Microsoft Autogen Studio Bing Search Tool
- Implementation:Nightwatchjs Nightwatch Web Element Type Definitions
- Implementation:Openai Openai node Responses InputItems
Heuristics
- Heuristic:CARLA simulator Carla PID Controller Tuning
- Heuristic:EvolvingLMMs Lab Lmms eval Request Caching Strategy
- Heuristic:Mlc ai Mlc llm GPU Memory Budget Tuning
- Heuristic:Triton inference server Server Dynamic Batching Tuning
- Heuristic:Vibrantlabsai Ragas Warning Deprecated V1 Metrics
- Heuristic:Apache Dolphinscheduler HikariCP Pool Tuning
- Heuristic:Microsoft DeepSpeedExamples SuperOffload NUMA Binding
- Heuristic:Fede1024 Rust rdkafka Commit Mode Sync Vs Async
- Heuristic:AUTOMATIC1111 Stable diffusion webui Cross Attention Memory Slicing
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
Environments
- Environment:Sdv dev SDV GPU CUDA Support
- Environment:Apache Dolphinscheduler Java Runtime
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:Openai Openai agents python Voice Dependencies
- Environment:Huggingface Alignment handbook Python Transformers
- Environment:Evidentlyai Evidently Grafana Monitoring Environment
- Environment:Openai CLIP PyTorch CUDA Runtime
- Environment:Mit han lab Llm awq Python Runtime Environment
- Environment:Unstructured IO Unstructured Ingest CLI
- Environment:Kubeflow Pipelines Kubernetes Cluster