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:Unstructured IO Unstructured Connector Ingest Pipeline
- Workflow:Deepset ai Haystack RAG Pipeline
- Workflow:Huggingface Diffusers Model Quantization
- Workflow:Iterative Dvc Remote Data Sync
- Workflow:AnswerDotAI RAGatouille Document Indexing And Search
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Lucidrains X transformers Non Autoregressive Masked Generation
- Workflow:Princeton nlp SimPO On Policy Data Generation
- Workflow:Treeverse LakeFS Data Version Control With Branches
- Workflow:CrewAIInc CrewAI Hierarchical Crew Execution
Principles
- Principle:Datajuicer Data juicer Dataset Loading
- Principle:Apache Druid Supervisor Health Monitoring
- Principle:Heibaiying BigData Notes HBase Connection Creation
- Principle:Huggingface Datasets Audio Feature Handling
- Principle:Microsoft Semantic kernel RAG Chat Augmentation
- Principle:Apache Airflow Configuration Resolution
- Principle:BerriAI Litellm Deployment Definition
- Principle:Huggingface Peft Adapter Injection
- Principle:SeldonIO Seldon core Pipeline Version Progression
- Principle:Apache Paimon Snapshot Management
Implementations
- Implementation:BerriAI Litellm Redact Messages
- Implementation:Sgl project Sglang CPU MoE INT4
- Implementation:PeterL1n BackgroundMattingV2 HomographicAlignment
- Implementation:Ray project Ray Deploy Jars
- Implementation:Scikit learn Scikit learn DictionaryLearning
- Implementation:Farama Foundation Gymnasium Vector RecordEpisodeStatistics
- Implementation:Lm sys FastChat Split Long Conversation
- Implementation:Datajuicer Data juicer ExtractTablesFromHtmlMapper
- Implementation:Cohere ai Cohere python StreamedChatResponse Union
- Implementation:FMInference FlexLLMGen DeepSpeed Runtime Config
Heuristics
- Heuristic:Neuml Txtai Memory Streaming Optimization
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Roboflow Rf detr Batch Size Memory Tradeoff
- Heuristic:Alibaba ROLL Reward Clipping Normalization
- Heuristic:Mbzuai oryx Awesome LLM Post training Paper Deduplication Via Dict
- Heuristic:Eric mitchell Direct preference optimization TF32 Matmul Precision
- Heuristic:Apache Airflow Variable Access Pattern
- Heuristic:LLMBook zh LLMBook zh github io DPO Beta Hyperparameter
- Heuristic:OpenRLHF OpenRLHF Value Head ZeRO3 Init Tip
- Heuristic:Mage ai Mage ai HTTP Error Classification
Environments
- Environment:Promptfoo Promptfoo Node Runtime
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:Axolotl ai cloud Axolotl Python Runtime
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:Marker Inc Korea AutoRAG Python 3 10 Runtime
- Environment:Alibaba MNN CPU Build Environment
- Environment:Tensorflow Tfjs Node Native Runtime
- Environment:OpenBMB UltraFeedback vLLM Multi GPU Environment
- Environment:CarperAI Trlx Python Accelerate
- Environment:Unslothai Unsloth CUDA BitsAndBytes