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:Confident ai Deepeval Component Level LLM Evaluation
- Workflow:Mage ai Mage ai SQL Database Source Extraction
- Workflow:Datajuicer Data juicer Text Data Processing Pipeline
- Workflow:Alibaba MNN Model Conversion Pipeline
- Workflow:Guardrails ai Guardrails Custom Validator Development
- Workflow:Langfuse Langfuse Dataset experiment pipeline
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:FMInference FlexLLMGen Single GPU Offloaded Inference
- Workflow:Spotify Luigi Database Ingestion Pipeline
- Workflow:MarketSquare Robotframework browser API Testing via Browser
Principles
- Principle:Anthropics Anthropic sdk python Stream Context Manager Setup
- Principle:Langchain ai Langgraph Graph Module Definition
- Principle:Huggingface Transformers Adapter Injection
- Principle:Deepspeedai DeepSpeed Pipeline Training Schedule
- Principle:Datahub project Datahub Event Filtering
- Principle:Huggingface Datasets Arrow File Reading
- Principle:Rapidsai Cuml Cluster Model Fitting
- Principle:EvolvingLMMs Lab Lmms eval Job Submission
- Principle:ArroyoSystems Arroyo Execution Engine
- Principle:Speechbrain Speechbrain LibriTTS Data Preparation
Implementations
- Implementation:Microsoft Onnxruntime OrtSession
- Implementation:NVIDIA TransformerEngine TE LayerNormMLP
- Implementation:Teamcapybara Capybara WhitespaceNormalizer
- Implementation:DevExpress Testcafe CommandFormatter
- Implementation:TobikoData Sqlmesh API Environments
- Implementation:Risingwavelabs Risingwave MetaClient
- Implementation:Vllm project Vllm Prometheus Metrics Endpoint
- Implementation:Eventual Inc Daft Daft Func Batch
- Implementation:Roboflow Rf detr RFDETR Predict
- Implementation:DataExpert io Data engineer handbook Pg restore Init Script
Heuristics
- Heuristic:Fede1024 Rust rdkafka Queue Buffering Priority
- Heuristic:Microsoft LoRA LoRA Rank Selection
- Heuristic:FlagOpen FlagEmbedding Gradient Checkpointing Tip
- Heuristic:Sdv dev SDV HMA Schema Simplification
- Heuristic:Rapidsai Cuml GPU Cache Alignment
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Triton inference server Server Server Default Configuration
- Heuristic:Apache Flink Hadoop Thread Safety Mutexes
- Heuristic:Huggingface Datatrove Thundering Herd Prevention
- Heuristic:Ucbepic Docetl Reduce Parallel Fold Tuning
Environments
- Environment:Webdriverio Webdriverio Cloud Service Credentials
- Environment:Lm sys FastChat SFT Training Environment
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:Openai Openai agents python LiteLLM Dependencies
- Environment:Sgl project Sglang ROCm
- Environment:Mistralai Client python Agents Environment
- Environment:Mlflow Mlflow GPU System Metrics Environment
- Environment:OWASP Www project top 10 for large language model applications PR Description Generator Runtime
- Environment:SqueezeAILab ETS Evaluation Python Stack
- Environment:Interpretml Interpret Blackbox Explainer Dependencies