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:ChenghaoMou Text dedup SimHash Deduplication
- Workflow:Pyro ppl Pyro Discrete Enumeration
- Workflow:Microsoft Agent framework Graph Based Workflow Execution
- Workflow:Vibrantlabsai Ragas Prompt Optimization
- Workflow:Junyanz Pytorch CycleGAN and pix2pix Pix2pix Training
- Workflow:Kubeflow Kubeflow AI Lifecycle Pipeline
- Workflow:Puppeteer Puppeteer Web Scraping And Interaction
- Workflow:Arize ai Phoenix Trace Ingestion Pipeline
- Workflow:Google deepmind Dm control Manipulation Task Setup
- Workflow:Gretelai Gretel synthetics DataFrame Batch Synthesis
Principles
- Principle:Online ml River Non Stationary Stream Loading
- Principle:AnswerDotAI RAGatouille Document Reranking
- Principle:Run llama Llama index Embedding Finetune Execution
- Principle:Axolotl ai cloud Axolotl Vision Language Model Loading
- Principle:MarketSquare Robotframework browser Page Navigation and Interaction
- Principle:Volcengine Verl SAPO Algorithm
- Principle:Testtimescaling Testtimescaling github io Course Branch Bootstrapping
- Principle:Ollama Ollama AgentArchitecture
- Principle:Cypress io Cypress Test Specification Authoring
- Principle:Cleanlab Cleanlab Segmentation Label Issue Filtering
Implementations
- Implementation:Apache Paimon CatalogTableType
- Implementation:BerriAI Litellm Litellm Global Configuration
- Implementation:Predibase Lorax Flash RoBERTa
- Implementation:NVIDIA NeMo Curator ContentTypeClassifier
- Implementation:InternLM Lmdeploy Action Tools
- Implementation:Openai Openai python Realtime Conversation Item Create
- Implementation:Infiniflow Ragflow Settings Constants
- Implementation:ArroyoSystems Arroyo Lookup Join
- Implementation:Cohere ai Cohere python Document Model
- Implementation:ARISE Initiative Robosuite RethinkGripper
Heuristics
- Heuristic:Lucidrains X transformers Gradient Clipping And Accumulation
- Heuristic:Langgenius Dify API Token Single Flight Caching
- Heuristic:Datahub project Datahub Validation Cross API
- Heuristic:DataTalksClub Data engineering zoomcamp DuckDB OOM Memory Management
- Heuristic:Astronomer Astronomer cosmos Watcher Queue Sizing
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Instance Norm for Multi GPU
- Heuristic:TobikoData Sqlmesh Forward Only Safety
- Heuristic:Predibase Lorax LoRA Kernel Selection By Rank
- Heuristic:Romsto Speculative Decoding Ngram Order Selection
- Heuristic:Apache Dolphinscheduler Epoll Vs NIO Selection
Environments
- Environment:Allenai Open instruct CUDA GPU Training
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Neuml Txtai API Server Configuration
- Environment:Spotify Luigi SQLAlchemy Database
- Environment:Sgl project Sglang Distributed
- Environment:Apache Flink Java Build Environment
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:Puppeteer Puppeteer Configuration Environment Variables
- Environment:Huggingface Alignment handbook Python TRL
- Environment:Facebookresearch Audiocraft Python PyTorch CUDA Environment