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:Explodinggradients Ragas Agent Evaluation
- Workflow:Microsoft Playwright AI agent driven testing
- Workflow:Datahub project Datahub Docker Quickstart Deployment
- Workflow:Explodinggradients Ragas RAG Evaluation
- Workflow:Apache Dolphinscheduler Datasource Plugin Development
- Workflow:SeleniumHQ Selenium Page Object Pattern Testing
- Workflow:Allenai Open instruct SFT Finetuning
- Workflow:Microsoft Playwright Codegen test recording
- Workflow:Tencent Ncnn Vulkan GPU Accelerated Inference
- Workflow:Haotian liu LLaVA Benchmark Evaluation
Principles
- Principle:Scikit learn Scikit learn Random Forest Classification
- Principle:Mlc ai Mlc llm Model Library Packaging
- Principle:Cohere ai Cohere python Message Construction
- Principle:Trailofbits Fickling Benchmark Payload Injection
- Principle:Huggingface Peft Cosine Similarity Contrastive Training
- Principle:Heibaiying BigData Notes Prepare Input Data
- Principle:ClickHouse ClickHouse DNS Resolution
- Principle:Google deepmind Dm control Robot Configuration
- Principle:Apache Beam Worker Initialization
- Principle:Sktime Pytorch forecasting Probabilistic Prediction
Implementations
- Implementation:Mlc ai Mlc llm Serve
- Implementation:InternLM Lmdeploy Gemm Format
- Implementation:OpenHands OpenHands UseArray
- Implementation:DataTalksClub Data engineering zoomcamp Dbt Test Docs CLI
- Implementation:Mit han lab Llm awq WQLinear from linear
- Implementation:Kornia Kornia Lovasz Hinge Loss
- Implementation:Mage ai Mage ai Google Ads Ads Schema
- Implementation:LMCache LMCache L1 Manager
- Implementation:Ggml org Llama cpp KV Cache ISWA
- Implementation:NVIDIA NeMo Curator ImageFilterBase
Heuristics
- Heuristic:Huggingface Datasets Cache Fingerprinting Tips
- Heuristic:Puppeteer Puppeteer Chrome Default Launch Arguments
- Heuristic:TobikoData Sqlmesh Model Change Categorization
- Heuristic:Datajuicer Data juicer Batch Size Adaptation
- Heuristic:Romsto Speculative Decoding KV Cache Instability
- Heuristic:SqueezeAILab ETS Thread Parallelism Suppression
- Heuristic:Nightwatchjs Nightwatch ESM Module Loading Tips
- Heuristic:Huggingface Trl DeepSpeed ZeRO3 Generation Tradeoff
- Heuristic:Helicone Helicone Rate Limiting Fail Open
- Heuristic:SeleniumHQ Selenium Warning Deprecated Proxy FTP Methods
Environments
- Environment:Microsoft Onnxruntime Distributed Training Environment
- Environment:Kubeflow Pipelines Python SDK
- Environment:Zai org CogVideo Diffusers Inference Environment
- Environment:DataExpert io Data engineer handbook PostgreSQL Docker Environment
- Environment:Huggingface Alignment handbook PyTorch CUDA
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA
- Environment:Shiyu coder Kronos Comet ML Logging
- Environment:CrewAIInc CrewAI LLM Provider Credentials
- Environment:Langfuse Langfuse Docker Infrastructure
- Environment:Testtimescaling Testtimescaling github io Semantic Scholar API