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:Recommenders team Recommenders News Recommendation NRMS
- Workflow:Allenai Open instruct GRPO Reinforcement Learning
- Workflow:Marker Inc Korea AutoRAG Pipeline Deployment
- Workflow:Apache Druid Visual Data Exploration
- Workflow:Explodinggradients Ragas LLM Benchmarking
- Workflow:Neuml Txtai Agent Execution
- Workflow:Triton inference server Server Quickstart Model Deployment
- Workflow:Togethercomputer Together python Embeddings And Reranking
- Workflow:Groq Groq python Streaming Chat Completion
- Workflow:Huggingface Optimum FX Graph Optimization
Principles
- Principle:Huggingface Transformers Environment Setup
- Principle:Iterative Dvc Dependency Graph Validation
- Principle:Bitsandbytes foundation Bitsandbytes FSDP Quant State Recovery
- Principle:Alibaba ROLL Knowledge Distillation Loss
- Principle:Avhz RustQuant Option Greeks
- Principle:Isaac sim IsaacGymEnvs RL Agent Initialization
- Principle:Iterative Dvc Experiment Comparison
- Principle:AUTOMATIC1111 Stable diffusion webui UI Architecture
- Principle:Apache Dolphinscheduler RPC Service Contract Definition
- Principle:Vespa engine Vespa Tokenization
Implementations
- Implementation:Sktime Pytorch forecasting SeriesDecomposition
- Implementation:Openai Openai agents python Dynamic System Prompt Pattern
- Implementation:Datajuicer Data juicer AudioNMFSNRFilter
- Implementation:Scikit learn contrib Imbalanced learn Pipeline
- Implementation:Datajuicer Data juicer Config All Yaml
- Implementation:DevExpress Testcafe Runner Fluent API
- Implementation:Facebookresearch Habitat lab UserMask
- Implementation:Unslothai Unsloth FastLanguageModel From Pretrained
- Implementation:CARLA simulator Carla RssCheck Interface
- Implementation:Alibaba ROLL Patcher
Heuristics
- Heuristic:LLMBook zh LLMBook zh github io Reward Model LM Regularization
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:Deepspeedai DeepSpeed Shared Memory Sizing
- Heuristic:Openai Openai python Streaming Resource Management
- Heuristic:Eric mitchell Direct preference optimization Activation Checkpointing Memory
- Heuristic:Allenai Open instruct BFloat16 Training
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:AnswerDotAI RAGatouille FAISS Vs PyTorch KMeans Indexing
- Heuristic:SeleniumHQ Selenium FindElements For Absence Check
- Heuristic:Gretelai Gretel synthetics Mixed Precision Training Tradeoff
Environments
- Environment:Openai Openai agents python MCP Dependencies
- Environment:Truera Trulens Streamlit Dashboard Environment
- Environment:Open compass VLMEvalKit Python Runtime Environment
- Environment:Marker Inc Korea AutoRAG API Keys Configuration
- Environment:Apache Spark Release Build Environment
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:Pyro ppl Pyro Visualization Tools
- Environment:Helicone Helicone Python ClickHouse Migrations
- Environment:Duckdb Duckdb Code Formatting Tools
- Environment:Triton inference server Server Docker Container Build