Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Truera Trulens RAG Evaluation With LangChain
- Workflow:Googleapis Python genai Multimodal Content Generation
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:Dotnet Machinelearning AutoML Experiment
- Workflow:Dotnet Machinelearning Time Series Forecasting
- Workflow:Confident ai Deepeval Component Level LLM Evaluation
- Workflow:Getgauge Taiko Form Interaction Testing
- Workflow:ChenghaoMou Text dedup SimHash Deduplication
- Workflow:Openai Openai python Realtime Conversation
- Workflow:Deepspeedai DeepSpeed Pipeline Parallel Training
Principles
- Principle:Open compass VLMEvalKit Environment Setup
- Principle:Obss Sahi COCO Dataset Loading
- Principle:Huggingface Diffusers Training Configuration
- Principle:Explodinggradients Ragas Experiment Versioning
- Principle:Ucbepic Docetl Prompt Iteration
- Principle:Pyro ppl Pyro Epidemiological Modeling
- Principle:Intel Ipex llm GaLore Gradient Projection
- Principle:Elevenlabs Elevenlabs python Conversational Session
- Principle:PeterL1n BackgroundMattingV2 Coarse matting prediction
- Principle:DevExpress Testcafe Fixture Declaration
Implementations
- Implementation:Evidentlyai Evidently Legacy UI Config
- Implementation:CARLA simulator Carla ActorBlueprint Class
- Implementation:Apache Paimon Lint Python Script
- Implementation:Predibase Lorax Merge Adapters Function
- Implementation:Spotify Luigi DockerTask
- Implementation:Scikit learn Scikit learn BaseEnsemble
- Implementation:Eventual Inc Daft Utils
- Implementation:Princeton nlp SimPO Trainer Save and Evaluate
- Implementation:Langchain ai Langchain BaseMemory
- Implementation:Openai Openai python Validators Framework
Heuristics
- Heuristic:Romsto Speculative Decoding Filler Top K Tuning
- Heuristic:TobikoData Sqlmesh Execution Time Caching
- Heuristic:Microsoft Autogen Parallel Tool Call Safety
- Heuristic:Ollama Ollama VRAM Recovery And Scheduling
- Heuristic:Mbzuai oryx Awesome LLM Post training API Rate Limit Retry Strategy
- Heuristic:PeterL1n BackgroundMattingV2 Data Augmentation Strategy
- Heuristic:Alibaba ROLL KL Coefficient Tuning
- Heuristic:Tencent Ncnn NMS Threshold Tuning
- Heuristic:AnswerDotAI RAGatouille Auto Batch Size For Long Documents
- Heuristic:Mlc ai Mlc llm Optimization Level Selection
Environments
- Environment:Haifengl Smile Native BLAS LAPACK ARPACK
- Environment:SeleniumHQ Selenium Selenium Manager Runtime
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Spotify Luigi Apache Spark
- Environment:Puppeteer Puppeteer Configuration Environment Variables
- Environment:Eventual Inc Daft Cloud Storage Credentials
- Environment:Lucidrains X transformers PyTorch CUDA
- Environment:Mlc ai Mlc llm WebGPU Browser Environment
- Environment:Lm sys FastChat SFT Training Environment
- Environment:Sgl project Sglang ROCm