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:LLMBook zh LLMBook zh github io DPO Alignment
- Workflow:Langchain ai Langgraph CLI Deployment
- Workflow:Infiniflow Ragflow Search Application Setup
- Workflow:Unstructured IO Unstructured Connector Ingest Pipeline
- Workflow:Datajuicer Data juicer Distributed Ray Processing
- Workflow:Evidentlyai Evidently Text Data Quality Evaluation
- Workflow:Togethercomputer Together python Chat Completion
- Workflow:Mistralai Client python Function Calling
- Workflow:Google deepmind Mujoco Offscreen video recording
- Workflow:Confident ai Deepeval End to End LLM Evaluation
Principles
- Principle:Nightwatchjs Nightwatch Extension Usage In Tests
- Principle:SeldonIO Seldon core Multi Modal Pipeline Composition
- Principle:Datajuicer Data juicer Statistics Key Definition
- Principle:Langfuse Langfuse OTel Endpoint Reception
- Principle:DataTalksClub Data engineering zoomcamp Dbt Intermediate Layer
- Principle:Cohere ai Cohere python Tool Function Execution
- Principle:Ucbepic Docetl Output Management
- Principle:Langgenius Dify Retrieval Testing
- Principle:Eventual Inc Daft Type Casting
- Principle:Deepspeedai DeepSpeed RLHF Checkpointing
Implementations
- Implementation:CarperAI Trlx Random Walk Environment
- Implementation:Apache Shardingsphere EtcdDistributedLock Lock
- Implementation:Hpcaitech ColossalAI ChineseTextSplitter
- Implementation:Mlc ai Mlc llm CLIP Vision
- Implementation:CARLA simulator Carla Map API Spec
- Implementation:MaterializeInc Materialize CLI Run
- Implementation:PacktPublishing LLM Engineers Handbook Create Train Test Split
- Implementation:Lance format Lance Java IndexOptions
- Implementation:Online ml River Datasets SolarFlare
- Implementation:Langchain ai Langchain Anthropic Model Profiles
Heuristics
- Heuristic:Anthropics Anthropic sdk python Streaming For Long Requests
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Huggingface Datasets Flatten Indices Performance
- Heuristic:Huggingface Datatrove Thundering Herd Prevention
- Heuristic:Evidentlyai Evidently Drift Detection Thresholds
- Heuristic:VainF Torch Pruning GQA Head Pruning Constraints
- Heuristic:Huggingface Datatrove MinHash Parameter Tuning
- Heuristic:Tensorflow Serving Resource Estimation Rules
- Heuristic:Kserve Kserve Prefix Cache Consistency
- Heuristic:Apache Airflow DAG Complexity Reduction
Environments
- Environment:Apache Druid Web Console Development
- Environment:Microsoft Agent framework Core Package Dependencies
- Environment:Triton inference server Server Docker Container Build
- Environment:Mbzuai oryx Awesome LLM Post training Python Matplotlib
- Environment:HKUDS AI Trader MCP Services
- Environment:Lance format Lance Rust Toolchain
- Environment:CARLA simulator Carla Build From Source Requirements
- Environment:DistrictDataLabs Yellowbrick Optional NLP Dependencies
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Datahub project Datahub Docker Runtime