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:Microsoft DeepSpeedExamples SuperOffload Finetuning
- Workflow:Microsoft Autogen Tool Augmented Agent
- Workflow:Elevenlabs Elevenlabs python Voice Cloning
- Workflow:Deepset ai Haystack Document Indexing Pipeline
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Anthropics Anthropic sdk python Extended Thinking Reasoning
- Workflow:Kubeflow Pipelines Pipeline Control Flow
- Workflow:Microsoft Playwright End to end test authoring
- Workflow:Scikit learn Scikit learn Hyperparameter Tuning
- Workflow:LaurentMazare Tch rs Pretrained Image Classification
Principles
- Principle:Run llama Llama index Finetuned Model Retrieval
- Principle:Duckdb Duckdb Source Package Building
- Principle:Getgauge Taiko Browser Closure
- Principle:Webdriverio Webdriverio Session Cleanup
- Principle:Vllm project Vllm Speculative Engine Initialization
- Principle:TobikoData Sqlmesh Incremental Model Definition
- Principle:CARLA simulator Carla Sensor Attachment
- Principle:Diagram of thought Diagram of thought Typed Protocol Configuration
- Principle:Interpretml Interpret Feature Binning And Discretization
- Principle:Sktime Pytorch forecasting Synthetic Data Generation
Implementations
- Implementation:Openai Openai node Node CJS Lockfile
- Implementation:MarketSquare Robotframework browser Response Util
- Implementation:Risingwavelabs Risingwave PostgresConnectorConfig
- Implementation:Avhz RustQuant AnalyticOptionPricer Greeks
- Implementation:Duckdb Duckdb Zstd Common
- Implementation:Open compass VLMEvalKit CreationMMBenchDataset
- Implementation:EvolvingLMMs Lab Lmms eval ScreenSpot Utils
- Implementation:Lm sys FastChat Vision Image
- Implementation:Langchain ai Langchain SandboxTests
- Implementation:Danijar Dreamerv3 Main Configuration
Heuristics
- Heuristic:Dotnet Machinelearning Tokenizer Caching Strategy
- Heuristic:Microsoft Agent framework Function Invocation Defaults
- Heuristic:Guardrails ai Guardrails Guard History Memory Management
- Heuristic:Eric mitchell Direct preference optimization TF32 Matmul Precision
- Heuristic:Truera Trulens Temperature Zero For Deterministic Scoring
- Heuristic:Alibaba ROLL GPU Memory Offload Strategy
- Heuristic:Apache Paimon Compression Tuning
- Heuristic:Explodinggradients Ragas Deprecation Migration Guide
- Heuristic:Zai org CogVideo DeepSpeed Checkpoint Conversion Tips
- Heuristic:Datajuicer Data juicer Batch Size Adaptation
Environments
- Environment:Google deepmind Mujoco MJX JAX Environment
- Environment:AUTOMATIC1111 Stable diffusion webui GPU Compute Backend
- Environment:Microsoft LoRA NLG Eval External Tools
- Environment:Facebookresearch Habitat lab SLURM Distributed Environment
- Environment:DataTalksClub Data engineering zoomcamp Dlt BigQuery Environment
- Environment:Microsoft Onnxruntime CPU Training Environment
- Environment:Sgl project Sglang Kubernetes
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Apache Kafka Release Toolchain Environment
- Environment:Promptfoo Promptfoo Node Runtime