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:EvolvingLMMs Lab Lmms eval Custom Model Integration
- Workflow:NVIDIA NeMo Curator Video Curation Pipeline
- Workflow:Puppeteer Puppeteer Web Scraping And Interaction
- Workflow:Ollama Ollama Model Registry Operations
- Workflow:Wandb Weave Prompt Management
- Workflow:AUTOMATIC1111 Stable diffusion webui LoRA network application
- Workflow:Cypress io Cypress E2E Test Execution
- Workflow:Ggml org Ggml Model Conversion And Quantization
- Workflow:NVIDIA TransformerEngine FP8 Training Quickstart
- Workflow:Neuml Txtai Workflow Orchestration
Principles
- Principle:FMInference FlexLLMGen HELM Dependency Installation
- Principle:Sktime Pytorch forecasting Object Registry
- Principle:Mlc ai Web llm Structured Output Parsing
- Principle:EvolvingLMMs Lab Lmms eval Regression Testing Principle
- Principle:DistrictDataLabs Yellowbrick PCA Projection
- Principle:Facebookresearch Habitat lab Benchmark Configuration
- Principle:Rapidsai Cuml Synthetic Dataset Generation
- Principle:CARLA simulator Carla Recording Event Querying
- Principle:Ggml org Ggml Quantization API
- Principle:Eventual Inc Daft Logging Configuration
Implementations
- Implementation:Hiyouga LLaMA Factory PPO Trainer
- Implementation:Explodinggradients Ragas Experiment Comparison Pattern
- Implementation:Datahub project Datahub FieldPath Schematron
- Implementation:Langfuse Langfuse ClickHouse Query Fragments
- Implementation:Openai Openai node Beta Realtime Sessions
- Implementation:Run llama Llama index FunctionCallingLLM
- Implementation:Apache Spark Mvn Clean Package
- Implementation:Apache Flink DefaultRollingPolicy Builder
- Implementation:FlagOpen FlagEmbedding Reinforced IR Data Utils
- Implementation:Langchain ai Langchain MistralAIEmbeddings
Heuristics
- Heuristic:PeterL1n BackgroundMattingV2 Data Augmentation Strategy
- Heuristic:Getgauge Taiko Element Actionability Checks
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:NVIDIA DALI Distributed Sharding Strategy
- Heuristic:Trailofbits Fickling Race Condition Prevention
- Heuristic:DevExpress Testcafe Browser Connection Timeouts
- Heuristic:Lance format Lance Vector Index Tuning
- Heuristic:Datahub project Datahub Spark Databricks Coalescing
- Heuristic:Infiniflow Ragflow Agent Max Rounds Strategy
- Heuristic:HKUDS AI Trader Market Type Auto Detection
Environments
- Environment:MarketSquare Robotframework browser Docker Container
- Environment:Vllm project Vllm AArch64 CPU
- Environment:Lm sys FastChat Python Core Dependencies
- Environment:Kubeflow Kubeflow Istio Certmanager Dex Environment
- Environment:Pola rs Polars Rust Build Environment
- Environment:FlowiseAI Flowise Database Environment
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:Lance format Lance Python Environment
- Environment:Huggingface Alignment handbook Evaluation Tools
- Environment:Fede1024 Rust rdkafka CI Test Runner