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:Protectai Llm guard PII Anonymization Deanonymization
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Speechbrain Speechbrain Whisper ASR Finetuning
- Workflow:Mage ai Mage ai SQL Database Source Extraction
- Workflow:Deepseek ai Janus Autoregressive Image Generation
- Workflow:Obss Sahi COCO Dataset Slicing
- Workflow:CrewAIInc CrewAI Custom Tool Integration
- Workflow:Guardrails ai Guardrails Streaming Validation
- Workflow:Iterative Dvc Data Tracking
- Workflow:Run llama Llama index Evaluation Pipeline
Principles
- Principle:Pyro ppl Pyro MCMC Convergence Diagnostics
- Principle:Ucbepic Docetl Pipeline Assembly And Execution
- Principle:Ucbepic Docetl Deterministic Code Operations
- Principle:Pyro ppl Pyro Learnable Parameters
- Principle:Junyanz Pytorch CycleGAN and pix2pix Dataset Factory Loading
- Principle:SqueezeAILab ETS ILP Node Selection
- Principle:DataExpert io Data engineer handbook Docker Environment Setup
- Principle:Facebookresearch Audiocraft Language Model Export
- Principle:Langchain ai Langgraph State Schema Definition
- Principle:SeleniumHQ Selenium Session Request Routing
Implementations
- Implementation:Ucbepic Docetl RfiResponseExplorer
- Implementation:Open compass VLMEvalKit HiPhODataset
- Implementation:Apache Druid ShowLog
- Implementation:Tensorflow Tfjs CPU ResizeBilinearGrad Kernel
- Implementation:Ggml org Llama cpp CI Run
- Implementation:HKUDS AI Trader Jina Search Tool
- Implementation:Open compass VLMEvalKit LongVITA
- Implementation:InternLM Lmdeploy Gemm DispatchCache
- Implementation:Online ml River Anomaly ThresholdFilter
- Implementation:Predibase Lorax Punica Ops Bindings
Heuristics
- Heuristic:Princeton nlp Tree of thought llm Global State Token Counting
- Heuristic:Pytorch Serve Batch Size Tuning
- Heuristic:Romsto Speculative Decoding Gamma Tuning
- Heuristic:LaurentMazare Tch rs Hidden Dimension Alignment
- Heuristic:OpenGVLab InternVL Packed Training Buffer Management
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:Arize ai Phoenix Warning Deprecated HallucinationEvaluator
- Heuristic:Datahub project Datahub Emitter Selection Strategy
- Heuristic:Scikit learn Scikit learn Feature Scaling Numerical Stability
- Heuristic:Haifengl Smile BFGS Convergence Tuning
Environments
- Environment:Apache Spark JDK Build Environment
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:Mistralai Client python Agents Environment
- Environment:VainF Torch Pruning YOLO Pruning Dependencies
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:DataExpert io Data engineer handbook Spark Iceberg Docker Environment
- Environment:Apache Paimon Cloud Storage Credentials
- Environment:ARISE Initiative Robomimic PyTorch CUDA Environment
- Environment:Mlc ai Mlc llm WebGPU Browser Environment