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:Openclaw Openclaw Docker Deployment
- Workflow:Datajuicer Data juicer LLM Powered Data Generation
- Workflow:Dotnet Machinelearning AutoML Experiment
- Workflow:Groq Groq python Streaming Chat Completion
- Workflow:Heibaiying BigData Notes Hive Data Warehouse Operations
- Workflow:Alibaba ROLL Agentic RL Training Pipeline
- Workflow:Unslothai Unsloth GRPO Reinforcement Learning
- Workflow:Mlc ai Web llm Structured Output Generation
- Workflow:Deepset ai Haystack Document Indexing Pipeline
- Workflow:ARISE Initiative Robomimic Training Policy From Demonstrations
Principles
- Principle:Langgenius Dify PluginArchitecture
- Principle:NVIDIA NeMo Aligner REINFORCE Actor Setup
- Principle:Openai Openai agents python RunState Serialization
- Principle:Apache Beam Pipeline Translation Twister2
- Principle:Microsoft Autogen Termination Conditions
- Principle:Tensorflow Tfjs Model Compilation
- Principle:ARISE Initiative Robosuite Omniverse Rendering
- Principle:Mistralai Client python Message Construction
- Principle:LaurentMazare Tch rs Transformer Architecture
- Principle:Princeton nlp SimPO Pipeline Inference
Implementations
- Implementation:LMCache LMCache Mooncake Lookup Client
- Implementation:Eventual Inc Daft DataFrame Count Rows
- Implementation:Marker Inc Korea AutoRAG Raw And Corpus Schema
- Implementation:Turboderp org Exllamav2 Ext QMatrix
- Implementation:Marker Inc Korea AutoRAG Extract Best Config
- Implementation:Tencent Ncnn Ruapu ISA Detection
- Implementation:Tencent Ncnn Cpu Feature Detection
- Implementation:Recommenders team Recommenders LightGCN
- Implementation:Datahub project Datahub ServerConfig
- Implementation:LMCache LMCache API Registry
Heuristics
- Heuristic:Bitsandbytes foundation Bitsandbytes Compressed Statistics Double Quantization
- Heuristic:Spotify Luigi Batch Parameter Aggregation
- Heuristic:LLMBook zh LLMBook zh github io IGNORE INDEX Loss Masking
- Heuristic:Danijar Dreamerv3 Adaptive Gradient Clipping
- Heuristic:Trailofbits Fickling Injection Mode Selection
- Heuristic:Dotnet Machinelearning Tokenizer Caching Strategy
- Heuristic:ThreeSR Awesome Inference Time Scaling Date Parsing Fallback Tip
- Heuristic:Risingwavelabs Risingwave Source Backoff Strategy
- Heuristic:Cohere ai Cohere python Tokenizer Cache With TTL
- Heuristic:Microsoft Autogen Parallel Tool Call Safety
Environments
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Vibrantlabsai Ragas Python 3 9 Core Environment
- Environment:NVIDIA TransformerEngine GPU Compute Capability
- Environment:Google research Deduplicate text datasets Python HuggingFace Environment
- Environment:Truera Trulens Streamlit Dashboard Environment
- Environment:OpenRLHF OpenRLHF Flash Attention Environment
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Rapidsai Cuml Python RAPIDS Stack
- Environment:Astronomer Astronomer cosmos Cosmos Airflow Configuration
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas