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:PrefectHQ Prefect AI Data Analyst Agent
- Workflow:DataTalksClub Data engineering zoomcamp Spark Batch Processing
- Workflow:Predibase Lorax Multi Adapter Merging
- Workflow:Zai org CogVideo Diffusers Text to Video Inference
- Workflow:Snorkel team Snorkel Slice Aware Training
- Workflow:Cleanlab Cleanlab Datalab Dataset Audit
- Workflow:Mit han lab Llm awq TinyChat LLM Deployment
- Workflow:Scikit learn Scikit learn Data Preprocessing Pipeline
- Workflow:Heibaiying BigData Notes Hadoop MapReduce Word Count
- Workflow:Fastai Fastbook Image Classification
Principles
- Principle:Teamcapybara Capybara RSpec Integration
- Principle:Ggml org Ggml Metal GPU Computation
- Principle:LaurentMazare Tch rs Adam Optimization
- Principle:Openai Openai agents python RunState Serialization
- Principle:Scikit learn contrib Imbalanced learn Sampler Compatibility Checking
- Principle:Openai Whisper Audio Padding And Trimming
- Principle:Kserve Kserve Disaggregated Deployment
- Principle:Microsoft BIPIA Defended Model Evaluation
- Principle:Ucbepic Docetl Chunk Processing
- Principle:Nightwatchjs Nightwatch Dependency Management
Implementations
- Implementation:Teamcapybara Capybara Spec Selector
- Implementation:Bentoml BentoML Start Functions
- Implementation:Langgenius Dify UninstallPlugin
- Implementation:Online ml River Optim Initializers
- Implementation:Scikit learn Scikit learn SpectralBiclustering
- Implementation:LaurentMazare Tch rs Neural Style Transfer
- Implementation:Microsoft Autogen CI Checks Workflow
- Implementation:CARLA simulator Carla Python Module Entry
- Implementation:Duckdb Duckdb Brotli Platform
- Implementation:Scikit learn Scikit learn ClassicalMDS
Heuristics
- Heuristic:CARLA simulator Carla Synchronous Mode Fixed Delta
- Heuristic:Sdv dev SDV CTGAN Column Performance
- Heuristic:Cypress io Cypress Browser Version Workarounds
- Heuristic:Alibaba ROLL Sequence Packing Alignment
- Heuristic:OWASP Www project top 10 for large language model applications Warning Deprecated Markdown To PDF Convert
- Heuristic:Zai org CogVideo DeepSpeed Checkpoint Conversion Tips
- Heuristic:Apache Kafka Log4j Migration Compatibility
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
- Heuristic:Triton inference server Server Documentation Standards
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Strategy Selection
Environments
- Environment:Rapidsai Cuml Dask Distributed
- Environment:Huggingface Transformers Python 310 Runtime
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA
- Environment:Datajuicer Data juicer Ray Cluster Environment
- Environment:Openai Openai agents python OpenAI API Credentials
- Environment:Vllm project Vllm ROCm
- Environment:Obss Sahi Python Detection Frameworks
- Environment:Apache Kafka JVM Runtime Environment
- Environment:Explodinggradients Ragas LLM Provider Environment