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:Intel Ipex llm vLLM Serving
- Workflow:Online ml River Drift Adaptive Classification
- Workflow:Rapidsai Cuml Random Forest Training And Inference
- Workflow:MaterializeInc Materialize Integration Test Development
- Workflow:Open compass VLMEvalKit Adding Custom VLM
- Workflow:Webdriverio Webdriverio Standalone Browser Automation
- Workflow:Helicone Helicone LLM Request Proxy Logging
- Workflow:FlowiseAI Flowise Document Store Ingestion
- Workflow:Mlc ai Mlc llm Python Engine Inference
- Workflow:Evidentlyai Evidently Data Drift Monitoring
Principles
- Principle:Helicone Helicone Plan Upgrade
- Principle:DevExpress Testcafe Browser Provider Selection
- Principle:Run llama Llama index Embedding Model Integration
- Principle:Unslothai Unsloth MoE Grouped GEMM
- Principle:SeleniumHQ Selenium Development Environment Setup
- Principle:Evidentlyai Evidently Data Drift Detection
- Principle:Promptfoo Promptfoo Provider Interface
- Principle:Hpcaitech ColossalAI GRPO Consumer Setup
- Principle:Facebookresearch Audiocraft Pretrained Compression Export
- Principle:Haotian liu LLaVA Conversation Prompt Construction
Implementations
- Implementation:Ucbepic Docetl PresidentialDebateDemo
- Implementation:Open compass VLMEvalKit VITAQwen2
- Implementation:Datajuicer Data juicer VggtMapper
- Implementation:Astronomer Astronomer cosmos ExasolUserPasswordProfileMapping
- Implementation:Elevenlabs Elevenlabs python WidgetTextContents
- Implementation:Datajuicer Data juicer VideoMotionScoreRaftFilter
- Implementation:Iterative Dvc Repo Data
- Implementation:Openai Openai node Node CJS Auto Lockfile
- Implementation:CARLA simulator Carla TrafficManagerLocal
- Implementation:TobikoData Sqlmesh TableDiff Help
Heuristics
- Heuristic:Zai org CogVideo CPU Offload Strategy
- Heuristic:FlagOpen FlagEmbedding Warning Deprecated Search Demo
- Heuristic:Apache Kafka JVM GC Tuning Defaults
- Heuristic:Snorkel team Snorkel Minimum Three LFs
- Heuristic:Huggingface Alignment handbook DPO Beta Selection
- Heuristic:Obss Sahi Overlap Ratio Selection
- Heuristic:Microsoft BIPIA Delta Weight CPU Loading
- Heuristic:Hiyouga LLaMA Factory LoRA DDP Configuration
- Heuristic:Princeton nlp Tree of thought llm Functools Partial Model Binding
- Heuristic:Fede1024 Rust rdkafka Main Queue Poll Interval
Environments
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Alibaba ROLL ROCm GPU Environment
- Environment:Kserve Kserve Knative Serving
- Environment:Eventual Inc Daft Cloud Storage Credentials
- Environment:Sail sg LongSpec Training Environment
- Environment:Kserve Kserve Python Runtime
- Environment:Snorkel team Snorkel SpaCy NLP
- Environment:Trailofbits Fickling PyTorch
- Environment:Apache Airflow Development Contributor Environment