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:Facebookresearch Audiocraft MusicGen Training Pipeline
- Workflow:Explodinggradients Ragas Test Data Generation
- Workflow:Huggingface Transformers Model Quantization
- Workflow:Norrrrrrr lyn WAInjectBench Image Prompt Injection Detection
- Workflow:Hiyouga LLaMA Factory Model Inference and Serving
- Workflow:Allenai Open instruct Tulu3 Full Post Training
- Workflow:Google research Deduplicate text datasets Single file deduplication
- Workflow:Fastai Fastbook NLP Text Classification
- Workflow:BerriAI Litellm Fine Tuning Job
- Workflow:Scikit learn contrib Imbalanced learn Ensemble Imbalanced Classification
Principles
- Principle:SeldonIO Seldon core HuggingFace Model Deployment And Verification
- Principle:Liu00222 Open Prompt Injection Input Preprocessing
- Principle:Apache Kafka JVM Configuration
- Principle:Openai Openai python Embedding Input Preparation
- Principle:Liu00222 Open Prompt Injection Binary Search Localization
- Principle:OpenBMB UltraFeedback Prompt Formatting
- Principle:Haifengl Smile Inference Request Processing
- Principle:Infiniflow Ragflow Knowledge Base Selection
- Principle:Allenai Open instruct vLLM Async Generation
- Principle:Apache Spark Container Image Build
Implementations
- Implementation:ArroyoSystems Arroyo Window Function
- Implementation:Teamcapybara Capybara WhitespaceNormalizer
- Implementation:Farama Foundation Gymnasium CartPoleFunctional
- Implementation:CrewAIInc CrewAI LlamaIndex Tool
- Implementation:Openai Openai python Easy Input Message Param
- Implementation:Evidentlyai Evidently Report Init
- Implementation:Vibrantlabsai Ragas Documentation Configuration
- Implementation:Shiyu coder Kronos WebUI App
- Implementation:Huggingface Diffusers Single File Loadable Classes
- Implementation:Kornia Kornia Motion Blur
Heuristics
- Heuristic:Lm sys FastChat Conversation Splitting Token Buffer
- Heuristic:Astronomer Astronomer cosmos Memory Optimised Imports
- Heuristic:Spotify Luigi Batch Parameter Aggregation
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:Hpcaitech ColossalAI Gradient Checkpointing Memory Tip
- Heuristic:Microsoft LoRA Warning Deprecated Legacy Examples
- Heuristic:Protectai Llm guard Lazy Scanner Loading
- Heuristic:Webdriverio Webdriverio Mobile Platform Differences
- Heuristic:MaterializeInc Materialize Docker Image Cache Lookup
- Heuristic:Apache Flink Hadoop Thread Safety Mutexes
Environments
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:CarperAI Trlx NeMo Megatron
- Environment:Mlc ai Web llm Node Build Toolchain
- Environment:Marker Inc Korea AutoRAG Python 3 10 Runtime
- Environment:Fastai Fastbook Sklearn Environment
- Environment:Apache Dolphinscheduler Database Backend
- Environment:Microsoft BIPIA Python CUDA GPU Environment
- Environment:DistrictDataLabs Yellowbrick Optional NLP Dependencies
- Environment:LLMBook zh LLMBook zh github io Data Processing Environment
- Environment:Nautechsystems Nautilus trader Asyncio Uvloop Event Loop