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 Playwright End to end test authoring
- Workflow:Scikit learn Scikit learn Hyperparameter Tuning
- Workflow:Microsoft Onnxruntime Distributed Model Training
- Workflow:Mage ai Mage ai Building a New Source Connector
- Workflow:Onnx Onnx External Data Handling
- Workflow:Getgauge Taiko Form Interaction Testing
- Workflow:ARISE Initiative Robomimic Trained Policy Evaluation
- Workflow:PrefectHQ Prefect AI Data Analyst Agent
- Workflow:Kubeflow Pipelines Pipeline Control Flow
- Workflow:Unslothai Unsloth Model Export And Deployment
Principles
- Principle:Allenai Open instruct SFT Data Processing
- Principle:Getgauge Taiko Element Assertion
- Principle:Microsoft BIPIA Defended Model Evaluation
- Principle:Pyro ppl Pyro Importance Sampling Inference
- Principle:Ollama Ollama OpenAI Embeddings And Listing
- Principle:FMInference FlexLLMGen DeepSpeed Configuration Autotuning
- Principle:Datahub project Datahub Event Filtering
- Principle:Vespa engine Vespa Initial Configuration Fetch
- Principle:Nightwatchjs Nightwatch Multi Page Composition
- Principle:Langgenius Dify TanStack Query Integration
Implementations
- Implementation:Anthropics Anthropic sdk python Messages Parse
- Implementation:Ollama Ollama MLXRunner Model Base
- Implementation:Openclaw Openclaw RunCli
- Implementation:Diagram of thought Diagram of thought Format Compliance Validator
- Implementation:Hpcaitech ColossalAI ExperienceMaker Base
- Implementation:Rapidsai Cuml Make Regression
- Implementation:Microsoft Onnxruntime JsPackageLock
- Implementation:Vllm project Vllm Ops Header
- Implementation:Mlc ai Mlc llm Model Metadata Impl
- Implementation:Langgenius Dify Service Explore
Heuristics
- Heuristic:EvolvingLMMs Lab Lmms eval Limit Flag Testing Only
- Heuristic:Puppeteer Puppeteer Navigation Race Condition Avoidance
- Heuristic:Mlc ai Web llm Tokenizer JSON Preference
- Heuristic:Ray project Ray Graceful Shutdown Timing
- Heuristic:Lm sys FastChat GPU Memory Allocation Strategy
- Heuristic:Confident ai Deepeval Dotenv Loading Order
- Heuristic:Liu00222 Open Prompt Injection PPL Threshold Tuning
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:Langgenius Dify API Token Single Flight Caching
- Heuristic:Tencent Ncnn Letterbox Vs Direct Resize
Environments
- Environment:Pytorch Serve DeepSpeed Environment
- Environment:Sktime Pytorch forecasting Core Python Dependencies
- Environment:Pola rs Polars Cloud Storage Environment
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Mistralai Client python GCP Deployment Environment
- Environment:Open compass VLMEvalKit Python Runtime Environment
- Environment:Kubeflow Kubeflow Kubernetes Cluster Environment
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:EvolvingLMMs Lab Lmms eval Python Runtime Environment
- Environment:Elevenlabs Elevenlabs python FFmpeg Mpv