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:Avhz RustQuant Yield Curve Construction
- Workflow:Langfuse Langfuse Evaluation pipeline
- Workflow:CrewAIInc CrewAI Custom Tool Integration
- Workflow:Huggingface Transformers Model Training With Trainer
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Online ml River Binary Classification Pipeline
- Workflow:Dagster io Dagster DSPy Optimization
- Workflow:Astronomer Astronomer cosmos Kubernetes dbt execution
- Workflow:Farama Foundation Gymnasium Agent Evaluation Recording
- Workflow:EvolvingLMMs Lab Lmms eval Custom Model Integration
Principles
- Principle:SeleniumHQ Selenium Git Branching Strategy
- Principle:Onnx Onnx Model Loading
- Principle:Huggingface Datasets CSV Export
- Principle:Mlflow Mlflow Prompt Alias Management
- Principle:Datahub project Datahub UI Access
- Principle:Zai org CogVideo SAT Inference Configuration
- Principle:Mlflow Mlflow Protobuf Code Generation
- Principle:Microsoft Agent framework Agent Specialization
- Principle:Tensorflow Serving Retry With Backoff
- Principle:Openai Evals LangChain Integration
Implementations
- Implementation:Microsoft Playwright WkInterceptableRequest
- Implementation:Neuml Txtai Textractor
- Implementation:Protectai Llm guard Output Bias
- Implementation:Huggingface Diffusers DreamBooth Dataset Class
- Implementation:Google deepmind Dm control Viewer Core
- Implementation:Sail sg LongSpec Bulma Slider
- Implementation:NVIDIA NeMo Curator Trafilatura Extractor
- Implementation:Promptfoo Promptfoo Environment Variables
- Implementation:OpenRLHF OpenRLHF PairWiseLoss
- Implementation:Apache Druid OpenRewrite Migration Recipes
Heuristics
- Heuristic:Interpretml Interpret Memory Budget Heuristic
- Heuristic:LMCache LMCache Prefix Based Retrieval Pattern
- Heuristic:Recommenders team Recommenders TensorFlow Session Ordering
- Heuristic:Ggml org Llama cpp GPU Layer Offloading Verification
- Heuristic:DataTalksClub Data engineering zoomcamp GCS Upload Timeout Workaround
- Heuristic:NVIDIA TransformerEngine Build Optimization Tips
- Heuristic:EvolvingLMMs Lab Lmms eval Bootstrap Iteration Optimization
- Heuristic:Fastai Fastbook Weight Decay Tuning
- Heuristic:FlowiseAI Flowise Heap Memory Configuration
- Heuristic:Predibase Lorax Flash Attention Backend Selection
Environments
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Mistralai Client python Azure Deployment Environment
- Environment:Scikit learn Scikit learn Python Runtime Environment
- Environment:OWASP Www project top 10 for large language model applications PR Description Generator Runtime
- Environment:Avdvg InjectGuard CUDA GPU
- Environment:Nautechsystems Nautilus trader Python Cython Rust Runtime
- Environment:Huggingface Transformers Python 310 Runtime
- Environment:Tencent Ncnn Build Environment
- Environment:Junyanz Pytorch CycleGAN and pix2pix Python PyTorch Runtime
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner