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:Microsoft Agent framework Multi Agent Concurrent Orchestration
- Workflow:Norrrrrrr lyn WAInjectBench Embedding Classifier Training
- Workflow:Apache Hudi Flink MOR Compaction
- Workflow:Langchain ai Langgraph Functional API Workflow
- Workflow:Volcengine Verl PPO Training With Reward Model
- Workflow:Neuml Txtai Agent Orchestration
- Workflow:Huggingface Alignment handbook Multi Stage Post Training
- Workflow:Vibrantlabsai Ragas Custom Metric Creation
- Workflow:ARISE Initiative Robosuite Environment Setup And Simulation
- Workflow:Roboflow Rf detr Roboflow Deployment
Principles
- Principle:Apache Flink File Commit Finalization
- Principle:Eventual Inc Daft AI Prompt Invocation
- Principle:ArroyoSystems Arroyo Connector Registry
- Principle:TobikoData Sqlmesh Backfill Strategy Selection
- Principle:Predibase Lorax Multi Process Server Launch
- Principle:ClickHouse ClickHouse Overflow Safe Arithmetic
- Principle:Huggingface Datasets Environment Reporting
- Principle:BerriAI Litellm Cache Initialization
- Principle:Microsoft DeepSpeedExamples ZeRO Inference Execution
- Principle:Infiniflow Ragflow Search Result Display
Implementations
- Implementation:Cohere ai Cohere python NonStreamedChatResponse Model
- Implementation:Ollama Ollama Convert Phi3
- Implementation:OpenGVLab InternVL Trainer Save Model
- Implementation:ArroyoSystems Arroyo Test Connection Table
- Implementation:Norrrrrrr lyn WAInjectBench process file
- Implementation:Eventual Inc Daft Convert Md To Notebook
- Implementation:Langgenius Dify PluginCredentialHooks
- Implementation:BerriAI Litellm Router Budget Limiter
- Implementation:Farama Foundation Gymnasium SwimmerEnv V4
- Implementation:Langgenius Dify Docker Compose Profiles
Heuristics
- Heuristic:Apache Dolphinscheduler Netty Thread Sizing
- Heuristic:Openai Openai python Warning Deprecated Legacy Response
- Heuristic:Mlc ai Mlc llm FlashInfer KV Cache Fallback
- Heuristic:Hiyouga LLaMA Factory Gradient Checkpointing Memory Optimization
- Heuristic:Langchain ai Langchain Text Splitter Separator Hierarchy
- Heuristic:Mit han lab Llm awq Skip QK Projection Clipping
- Heuristic:Unslothai Unsloth Gradient Accumulation Accuracy
- Heuristic:Wandb Weave Batch Processing Tuning
- Heuristic:AUTOMATIC1111 Stable diffusion webui UNet Performance Patches
- Heuristic:Roboflow Rf detr EMA Best Checkpoint Strategy
Environments
- Environment:Facebookresearch Audiocraft FAD TensorFlow Environment
- Environment:DataTalksClub Data engineering zoomcamp Kafka Confluent Environment
- Environment:Unstructured IO Unstructured GitHub Actions
- Environment:TobikoData Sqlmesh GitHub CICD Runner
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies
- Environment:Vespa engine Vespa FNET Transport Config
- Environment:Microsoft Semantic kernel ONNX CUDA Environment
- Environment:Allenai Open instruct Ray Distributed
- Environment:Lm sys FastChat API Keys And Credentials
- Environment:LMCache LMCache Python Runtime