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:Deepseek ai Janus Rectified Flow Image Generation
- Workflow:Tensorflow Serving Model Version Management
- Workflow:Princeton nlp Tree of thought llm ToT BFS experiment
- Workflow:Sdv dev SDV Single table synthesis
- Workflow:HKUDS AI Trader Multi Agent Comparison
- Workflow:Open compass VLMEvalKit Image Benchmark Evaluation
- Workflow:NVIDIA TransformerEngine FSDP Distributed Training
- Workflow:Sgl project Sglang Multimodal Vision Language Inference
- Workflow:Iterative Dvc Plot Visualization
- Workflow:DataExpert io Data engineer handbook AB Experimentation Server
Principles
- Principle:InternLM Lmdeploy Batch Text Generation
- Principle:Huggingface Optimum Library Logging Configuration
- Principle:PeterL1n BackgroundMattingV2 Dataset composition
- Principle:Norrrrrrr lyn WAInjectBench LLaVA Model Initialization
- Principle:Nightwatchjs Nightwatch Core Type System
- Principle:Apache Spark Programmatic Application Launch
- Principle:EvolvingLMMs Lab Lmms eval Queue Monitoring
- Principle:DevExpress Testcafe CI Reporter And Artifacts
- Principle:Huggingface Datasets Label Classification
- Principle:ARISE Initiative Robosuite Object Modeling
Implementations
- Implementation:Promptfoo Promptfoo Cache Migration
- Implementation:Tencent Ncnn YOLO11 Seg Example
- Implementation:Predibase Lorax SGMV Shrink Kernel
- Implementation:Risingwavelabs Risingwave UseFetch Hook
- Implementation:Turboderp org Exllamav2 Build Wheels Release Torch Latest
- Implementation:VainF Torch Pruning Count Ops And Params
- Implementation:Openai Openai node Translations Create
- Implementation:Open compass VLMEvalKit LLama3Mixsense
- Implementation:Cohere ai Cohere python RerankResponse Model
- Implementation:Cypress io Cypress RunModule Start
Heuristics
- Heuristic:Iamhankai Forest of Thought UCB Exploration Constant
- Heuristic:SeleniumHQ Selenium Bazel Hermetic Build Requirement
- Heuristic:Obss Sahi Match Threshold Tuning
- Heuristic:EvolvingLMMs Lab Lmms eval Distributed Padding Strategy
- Heuristic:FlowiseAI Flowise Tool Ordering Convention
- Heuristic:ClickHouse ClickHouse ThinLTO Build Tradeoffs
- Heuristic:Cypress io Cypress V8 Snapshot Memory
- Heuristic:Lm sys FastChat Flash Attention GPU Requirements
- Heuristic:ARISE Initiative Robosuite Hard Reset Vs Soft Reset
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
Environments
- Environment:Eric mitchell Direct preference optimization PyTorch CUDA
- Environment:Marker Inc Korea AutoRAG Japanese NLP Dependencies
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention
- Environment:Tensorflow Serving Docker Runtime Environment
- Environment:Helicone Helicone Wrangler CLI
- Environment:Google research Deduplicate text datasets Python TFDS Environment
- Environment:Truera Trulens Streamlit Dashboard Environment
- Environment:Openai Openai agents python Python 3 9 Runtime
- Environment:NVIDIA DALI CMake Build Environment
- Environment:Infiniflow Ragflow Python Runtime