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:Tencent Ncnn PyTorch Model Conversion and Inference
- Workflow:Lance format Lance Full Text Search
- Workflow:Explodinggradients Ragas Metric Prompt Optimization
- Workflow:Triton inference server Server LLM Deployment With TRT LLM
- Workflow:Infiniflow Ragflow Document Processing Pipeline
- Workflow:Princeton nlp SimPO SimPO Training
- Workflow:Mlc ai Web llm Basic Chat Completion
- Workflow:Lance format Lance Vector Search Pipeline
- Workflow:Mlc ai Web llm Web Worker Deployment
- Workflow:DataExpert io Data engineer handbook Flink Kafka Streaming Pipeline
Principles
- Principle:Langfuse Langfuse Batch Export Format Transformation
- Principle:Datahub project Datahub CLI Package Installation
- Principle:NVIDIA TransformerEngine FSDP Integration
- Principle:FMInference FlexLLMGen Runtime Utility Functions
- Principle:Scikit learn Scikit learn Score Distribution Analysis
- Principle:Ray project Ray Ray Runtime Initialization
- Principle:Huggingface Datasets Struct Flattening
- Principle:InternLM Lmdeploy Image Loading
- Principle:Princeton nlp SimPO Multi Seed Response Generation
- Principle:Cypress io Cypress Code Quality Verification
Implementations
- Implementation:NVIDIA NeMo Curator CommonCrawlDownloadExtractStage
- Implementation:ArroyoSystems Arroyo Pnpm Lockfile
- Implementation:Intel Ipex llm NPU Model Convert
- Implementation:Treeverse LakeFS Java SDK ObjectsApi
- Implementation:Protectai Llm guard Input BanCompetitors
- Implementation:FlowiseAI Flowise NavItem
- Implementation:Tencent Ncnn Mat Pixel Android
- Implementation:Langgenius Dify Service Base
- Implementation:Bentoml BentoML Framework Transformers
- Implementation:Langgenius Dify UseDocumentTitle
Heuristics
- Heuristic:Bigscience workshop Petals NF4 Quantization Default On CUDA
- Heuristic:Duckdb Duckdb Build Parallelism Tuning
- Heuristic:Lucidrains X transformers Sampling Temperature Strategy
- Heuristic:Wandb Weave Payload Size Limits
- Heuristic:Shiyu coder Kronos Instance Normalization Clipping
- Heuristic:Microsoft Autogen Agent Thread Safety
- Heuristic:Dotnet Machinelearning Tokenizer Caching Strategy
- Heuristic:SqueezeAILab ETS Thread Parallelism Suppression
- Heuristic:Cypress io Cypress Timeout Tuning
- Heuristic:Gretelai Gretel synthetics Parallel Generation CUDA Disable
Environments
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Google deepmind Dm control Python MuJoCo Runtime
- Environment:Mlfoundations Open flamingo PyTorch CUDA Distributed
- Environment:Intel Ipex llm vLLM XPU Serving Environment
- Environment:PacktPublishing LLM Engineers Handbook Python 3 11 Poetry Environment
- Environment:Alibaba MNN Python Export Environment
- Environment:Huggingface Datasets SQL Dependencies
- Environment:Kserve Kserve SRIOV RDMA Network
- Environment:Apache Paimon Optional Extensions
- Environment:Gretelai Gretel synthetics Python Base Environment