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:Sgl project Sglang Multimodal Vision Language Inference
- Workflow:Zai org CogVideo Diffusers Image to Video Inference
- Workflow:OpenBMB UltraFeedback GPT4 Preference Annotation
- Workflow:Bigscience workshop Petals Prompt Tuning Chatbot
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:Vespa engine Vespa Logging framework initialization
- Workflow:Deepseek ai Janus Multimodal Understanding
- Workflow:Shiyu coder Kronos Batch Prediction
- Workflow:Huggingface Datasets Dataset Preprocessing
- Workflow:Lance format Lance Full Text Search
Principles
- Principle:Online ml River Imbalanced Learning
- Principle:Tensorflow Serving SavedModel Export
- Principle:CrewAIInc CrewAI Crew Assembly
- Principle:NVIDIA NeMo Curator Image Export
- Principle:Heibaiying BigData Notes Hive Query Execution
- Principle:Avhz RustQuant Curve Interpolation
- Principle:Mbzuai oryx Awesome LLM Post training Keyword Data Loading
- Principle:Speechbrain Speechbrain HiFi GAN Vocoder Training
- Principle:Langgenius Dify Docker Deployment
- Principle:LaurentMazare Tch rs Token Embedding
Implementations
- Implementation:Evidentlyai Evidently Legacy Data Loader
- Implementation:Langchain ai Langchain RetrieversIntegrationTests
- Implementation:Infiniflow Ragflow SvgIcon Component
- Implementation:Puppeteer Puppeteer Injected TextContent
- Implementation:Confident ai Deepeval KeyFileHandler
- Implementation:TA Lib Ta lib python Stream Validation Pattern
- Implementation:Tencent Ncnn Ncnnmerge
- Implementation:OpenHands OpenHands Accordion
- Implementation:Bentoml BentoML Serve Multi Service
- Implementation:LLMBook zh LLMBook zh github io VLLM LLM Generate
Heuristics
- Heuristic:Bigscience workshop Petals Batch Splitting Threshold
- Heuristic:Cohere ai Cohere python Tokenizer Cache With TTL
- Heuristic:ARISE Initiative Robosuite Numba BSOD Workaround
- Heuristic:Kubeflow Kubeflow Sequential Infrastructure Deployment
- Heuristic:Microsoft Agent framework PowerFx Python Version Limit
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:Liu00222 Open Prompt Injection PPL Threshold Tuning
- Heuristic:Allenai Open instruct GPU Memory Utilization
- Heuristic:Elevenlabs Elevenlabs python VAD vs Manual Commit Strategy
- Heuristic:Marker Inc Korea AutoRAG Deterministic Evaluation Generation
Environments
- Environment:Kserve Kserve Leader Worker Set
- Environment:SeleniumHQ Selenium Selenium Manager Runtime
- Environment:Huggingface Transformers Flash Attention 2 Env
- Environment:Sgl project Sglang Performance Dashboard
- Environment:Guardrails ai Guardrails LLM Provider API Keys
- Environment:Iterative Dvc Python Runtime
- Environment:ChenghaoMou Text dedup Suffix Array External Tools
- Environment:Openai Openai agents python Voice Dependencies
- Environment:Alibaba ROLL DeepSpeed Training Environment
- Environment:Huggingface Alignment handbook Python Datasets