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:Openai Openai agents python Guardrails Secured Agent
- Workflow:Cleanlab Cleanlab Token Classification Label Quality
- Workflow:Iterative Dvc Experiment Tracking
- Workflow:Tencent Ncnn PyTorch Model Conversion and Inference
- Workflow:CARLA simulator Carla Simulation Recording and Replay
- Workflow:DataTalksClub Data engineering zoomcamp Spark Batch Processing
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:Huggingface Diffusers DreamBooth Personalization
- Workflow:Huggingface Datatrove Dataset Tokenization
- Workflow:Datahub project Datahub Java SDK Metadata Emission
Principles
- Principle:Roboflow Rf detr Training Loop Execution
- Principle:Unslothai Unsloth MoE Grouped GEMM
- Principle:Apache Beam Result Collection
- Principle:Huggingface Datatrove Token Counting
- Principle:Diagram of thought Diagram of thought Final Synthesis
- Principle:Microsoft Playwright Execute and Analyze Agent Results
- Principle:AnswerDotAI RAGatouille Hard Negative Mining
- Principle:Datahub project Datahub OpenLineage Conversion
- Principle:FMInference FlexLLMGen Autotuning Configuration Search
- Principle:Heibaiying BigData Notes Flink Kafka Source
Implementations
- Implementation:Sktime Pytorch forecasting QuantileLoss
- Implementation:Teamcapybara Capybara RackTest Node
- Implementation:Online ml River Rules AMRules
- Implementation:Lm sys FastChat Condense Rotary Embedding
- Implementation:Microsoft Onnxruntime Checkpoint Save Load
- Implementation:Predibase Lorax Flash Solar Modeling
- Implementation:Openai Openai node Videos Resource
- Implementation:Vespa engine Vespa Embedder Embed
- Implementation:Microsoft Autogen Studio AppInitializer
- Implementation:Sktime Pytorch forecasting Baseline
Heuristics
- Heuristic:Tensorflow Serving Model Warmup Strategy
- Heuristic:OpenRLHF OpenRLHF vLLM Embedding Resize Warning
- Heuristic:Vllm project Vllm Batch Size Hardware Scaling
- Heuristic:MarketSquare Robotframework browser Windows Shell NPM Workaround
- Heuristic:Intel Ipex llm LoRA Target All Linear Layers
- Heuristic:CrewAIInc CrewAI RAG Search Defaults
- Heuristic:Apache Paimon File Sizing and Split Planning
- Heuristic:Obss Sahi Warning Deprecated Legacy NMS
- Heuristic:Isaac sim IsaacGymEnvs Factory Velocity Limits
- Heuristic:Allenai Open instruct NCCL CUMEM Disable
Environments
- Environment:Fede1024 Rust rdkafka Kafka Broker Runtime
- Environment:Mistralai Client python Azure Deployment Environment
- Environment:ARISE Initiative Robomimic PyTorch CUDA Environment
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:Fastai Fastbook Python FastAI Environment
- Environment:Kornia Kornia CUDA GPU Environment
- Environment:ARISE Initiative Robomimic HuggingFace Hub Dependencies
- Environment:LLMBook zh LLMBook zh github io Data Processing Environment
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:FlowiseAI Flowise Queue Mode Environment