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:DataTalksClub Data engineering zoomcamp Spark Batch Processing
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:Fede1024 Rust rdkafka At Least Once Processing
- Workflow:Groq Groq python Chat Completion
- Workflow:Apache Kafka Coordinator Runtime Lifecycle
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:Neuml Txtai Semantic Search Pipeline
- Workflow:MarketSquare Robotframework browser API Testing via Browser
- Workflow:Roboflow Rf detr Roboflow Deployment
- Workflow:TobikoData Sqlmesh Model development and testing
Principles
- Principle:Pytorch Serve Pipeline Parallelism
- Principle:Microsoft Agent framework YAML Agent Schema
- Principle:Neuml Txtai Document Collection
- Principle:Openai Openai agents python Shared Context
- Principle:Elevenlabs Elevenlabs python Audio Playback
- Principle:PacktPublishing LLM Engineers Handbook Vector Storage
- Principle:Deepset ai Haystack LLM Chat Generation
- Principle:Tensorflow Tfjs Training Data Preparation
- Principle:InternLM Lmdeploy AWQ Weight Quantization
- Principle:Nightwatchjs Nightwatch Cucumber Runner Configuration
Implementations
- Implementation:Ollama Ollama XCreate Quantize
- Implementation:Microsoft Autogen AssistantAgent On Messages Stream
- Implementation:NVIDIA NeMo Curator Fuzzy IdentifyDuplicatesStage
- Implementation:Mlc ai Mlc llm RNN State
- Implementation:Datajuicer Data juicer NestedAggregator
- Implementation:OpenHands OpenHands GithubIssue Initialize Conversation
- Implementation:Online ml River Neighbors LazySearch
- Implementation:Cohere ai Cohere python TrainingStepMetrics
- Implementation:Online ml River Proba Beta
- Implementation:Datajuicer Data juicer CleanLinksMapper
Heuristics
- Heuristic:Allenai Open instruct GPU Memory Utilization
- Heuristic:LMCache LMCache Chunk Size And Default Config
- Heuristic:DistrictDataLabs Yellowbrick NaN Data Handling
- Heuristic:Tensorflow Serving Resource Estimation Rules
- Heuristic:Kserve Kserve Prefix Cache Consistency
- Heuristic:Mage ai Mage ai HTTP Request Timeout Defaults
- Heuristic:Liu00222 Open Prompt Injection Defense Strategy Selection
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:Nautechsystems Nautilus trader Cache Buffer Interval Tuning
- Heuristic:Deepspeedai DeepSpeed ZeRO Pipeline Incompatibility
Environments
- Environment:Pyro ppl Pyro Visualization Tools
- Environment:PrefectHQ Prefect AI Integration Credentials
- Environment:Spotify Luigi AWS S3 Storage
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:Snorkel team Snorkel PySpark
- Environment:Eric mitchell Direct preference optimization HuggingFace Transformers
- Environment:OpenGVLab InternVL DeepSpeed
- Environment:Arize ai Phoenix OpenTelemetry SDK
- Environment:Google research Deduplicate text datasets Python HuggingFace Environment
- Environment:Marker Inc Korea AutoRAG Japanese NLP Dependencies