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:Anthropics Anthropic sdk python Tool Use Integration
- Workflow:Mlc ai Web llm Structured Output Generation
- Workflow:Explodinggradients Ragas RAG Evaluation
- Workflow:Langchain ai Langchain Release Process
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Translation
- Workflow:FMInference FlexLLMGen Single GPU Offloaded Inference
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:DistrictDataLabs Yellowbrick Feature Analysis and Selection
- Workflow:Apache Shardingsphere Metadata DDL Refresh
- Workflow:PrefectHQ Prefect Database Cleanup With Approval
Principles
- Principle:Heibaiying BigData Notes Flink External Sink
- Principle:Alibaba MNN Model Format Conversion
- Principle:Apache Hudi Result Delivery
- Principle:Langchain ai Langgraph Runtime Context
- Principle:Spotify Luigi URI Target Resolution
- Principle:Bentoml BentoML Container Image Building
- Principle:Apache Kafka JIRA Reference Standardization
- Principle:Ollama Ollama GGUF Model Conversion DeepSeekOcr
- Principle:Haifengl Smile File Data Loading
- Principle:Ray project Ray Cross Language Task Submission
Implementations
- Implementation:Huggingface Datatrove TokensCounter
- Implementation:LMCache LMCache Distributed API
- Implementation:Togethercomputer Together python Rerank Create
- Implementation:Risingwavelabs Risingwave DynMethods
- Implementation:Microsoft Autogen Studio Builder Nodes
- Implementation:SeleniumHQ Selenium Closure EventHandler
- Implementation:MaterializeInc Materialize Helm Operator Values
- Implementation:Confident ai Deepeval AnswerRelevancyMetric
- Implementation:OpenRLHF OpenRLHF DPOLoss
- Implementation:Huggingface Trl RewardTrainer Prepare Dataset
Heuristics
- Heuristic:Huggingface Open r1 vLLM GPU Allocation
- Heuristic:SeldonIO Seldon core Model Scheduling Preference Tip
- Heuristic:Dagster io Dagster Batch Size Tuning
- Heuristic:Sdv dev SDV CTGAN Column Performance
- Heuristic:ClickHouse ClickHouse ThinLTO Build Tradeoffs
- Heuristic:ThreeSR Awesome Inference Time Scaling Date Parsing Fallback Tip
- Heuristic:Roboflow Rf detr Small Dataset Oversampling
- Heuristic:SeldonIO Seldon core Model Load Timeout Tip
- Heuristic:Truera Trulens Trace Compression Token Limits
- Heuristic:Fede1024 Rust rdkafka Commit Mode Sync Vs Async
Environments
- Environment:Alibaba ROLL Megatron Training Environment
- Environment:ARISE Initiative Robosuite MuJoCo Python
- Environment:Openclaw Openclaw Gateway Network Ports
- Environment:Vllm project Vllm Benchmarks
- Environment:Apache Airflow Docker Container Environment
- Environment:Langgenius Dify Credentials And Env Vars
- Environment:CarperAI Trlx NeMo Megatron
- Environment:DataExpert io Data engineer handbook Spark Iceberg Docker Environment
- Environment:Kubeflow Pipelines Kubernetes Cluster
- Environment:OpenBMB UltraFeedback vLLM Multi GPU Environment