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:Iamhankai Forest of Thought FoT Benchmark Evaluation
- Workflow:Duckdb Duckdb Building From Source
- Workflow:Huggingface Datasets Dataset Preprocessing
- Workflow:Unslothai Unsloth Vision Model Finetuning
- Workflow:Rapidsai Cuml Time Series Forecasting
- Workflow:Puppeteer Puppeteer Cross Browser Automation
- Workflow:Eventual Inc Daft Data Lakehouse ETL
- Workflow:ContextualAI HALOs Model Evaluation
- Workflow:Ggml org Llama cpp OpenAI Compatible Server
- Workflow:Cohere ai Cohere python AWS Bedrock Deployment
Principles
- Principle:Microsoft Playwright Implement Response Fixtures
- Principle:ClickHouse ClickHouse Installation
- Principle:CARLA simulator Carla PID Vehicle Control
- Principle:TobikoData Sqlmesh Environment Creation
- Principle:MarketSquare Robotframework browser Response Formatting and Validation
- Principle:Turboderp org Exllamav2 Sampling Configuration
- Principle:Mlc ai Web llm Chat Inference
- Principle:Rapidsai Cuml Linear Model Fitting
- Principle:Pyro ppl Pyro Simulator Based Inference
- Principle:Mistralai Client python SDK Installation
Implementations
- Implementation:Openai Openai agents python ItemHelpers
- Implementation:Langgenius Dify Tailwind Common Config
- Implementation:EvolvingLMMs Lab Lmms eval IFEval Instructions Registry
- Implementation:Microsoft Onnxruntime OrtCUDAProviderOptions
- Implementation:Fastai Fastbook Text Classifier Learner
- Implementation:Treeverse LakeFS Java SDK Model InstallationUsageReport
- Implementation:Facebookresearch Audiocraft MagnetSolver
- Implementation:Vllm project Vllm Dynamic 4bit Int MoE CPU
- Implementation:Kubeflow Kubeflow Profile CRD RBAC Setup
- Implementation:Deepspeedai DeepSpeed Evoformer MMA Multistage
Heuristics
- Heuristic:Protectai Llm guard PyTorch Compile Warmup
- Heuristic:Kornia Kornia Lazy Loading Optional Deps
- Heuristic:Sdv dev SDV Gaussian KDE Incompatibility
- Heuristic:Huggingface Datasets Num Proc Guidelines
- Heuristic:Cohere ai Cohere python HTTP Retry Backoff Strategy
- Heuristic:ThreeSR Awesome Inference Time Scaling Date Parsing Fallback Tip
- Heuristic:Sdv dev SDV Sampling Retry Tuning
- Heuristic:Datahub project Datahub Gradle Task Only
- Heuristic:Lm sys FastChat Flash Attention GPU Requirements
- Heuristic:Romsto Speculative Decoding Seed Fixing For Reproducibility
Environments
- Environment:Huggingface Optimum Tensor Parallelization Environment
- Environment:Deepspeedai DeepSpeed Python Runtime Environment
- Environment:Rapidsai Cuml Dask Distributed
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Alibaba ROLL Ascend NPU Environment
- Environment:Ggml org Ggml Python Tooling Environment
- Environment:Microsoft Autogen Python Runtime Environment
- Environment:Nightwatchjs Nightwatch Selenium WebDriver 4
- Environment:Huggingface Peft Python Core Dependencies
- Environment:Mlflow Mlflow Python Runtime Environment