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:Googleapis Python genai Text Content Generation
- Workflow:Openai Openai python Image Generation
- Workflow:MarketSquare Robotframework browser Browser Test Authoring
- Workflow:Google deepmind Dm control Composer Environment Building
- Workflow:ARISE Initiative Robomimic Training Policy From Demonstrations
- Workflow:Deepspeedai DeepSpeed Sequence Parallel Long Context Training
- Workflow:Groq Groq python Chat Completion
- Workflow:Apache Spark Standalone Cluster Deployment
- Workflow:Eventual Inc Daft Multimodal AI Batch Inference
- Workflow:Marker Inc Korea AutoRAG Evaluation Data Creation
Principles
- Principle:Guardrails ai Guardrails Observability
- Principle:BerriAI Litellm Health Monitoring
- Principle:Infiniflow Ragflow Search Configuration
- Principle:NVIDIA TransformerEngine Fused LayerNorm MLP
- Principle:Lance format Lance Text Data Preparation
- Principle:Iamhankai Forest of Thought Monte Carlo Tree Search
- Principle:Obss Sahi Image Slicing
- Principle:Speechbrain Speechbrain Beam Search Decoding
- Principle:Apache Airflow Scheduling Configuration
- Principle:Alibaba MNN Weight Quantization
Implementations
- Implementation:Mistralai Client python Pip Install Mistralai
- Implementation:OpenHands OpenHands Summarize Issue Solvability
- Implementation:Cohere ai Cohere python AwsGeneration
- Implementation:SeleniumHQ Selenium Closure Math Rect
- Implementation:DataTalksClub Data engineering zoomcamp Spark WithColumnRenamed
- Implementation:ClickHouse ClickHouse Common Library Build
- Implementation:DataExpert io Data engineer handbook Do team vertex transformation
- Implementation:Mlc ai Web llm Web Worker Chat Completion
- Implementation:FlowiseAI Flowise Register
- Implementation:Treeverse LakeFS UploadObject
Heuristics
- Heuristic:Ray project Ray Serve Concurrency And Backpressure
- Heuristic:Microsoft Autogen Agent Thread Safety
- Heuristic:Microsoft Semantic kernel Function Choice Behavior Selection
- Heuristic:NVIDIA DALI Distributed Sharding Strategy
- Heuristic:CARLA simulator Carla Synchronous Mode Fixed Delta
- Heuristic:Recommenders team Recommenders SAR Cold Start Items
- Heuristic:Groq Groq python Streaming Usage Stats
- Heuristic:Openai CLIP L2 Normalization For Cosine Similarity
- Heuristic:MaterializeInc Materialize CI Agent Prioritization
- Heuristic:Truera Trulens Trace Compression Token Limits
Environments
- Environment:Ray project Ray CI Build Matrix Environment
- Environment:Sgl project Sglang ROCm
- Environment:Tencent Ncnn Build Environment
- Environment:Sgl project Sglang CUDA
- Environment:AUTOMATIC1111 Stable diffusion webui Xformers Attention
- Environment:OpenRLHF OpenRLHF CUDA GPU Environment
- Environment:Huggingface Transformers 3D Parallel Multi GPU
- Environment:Open compass VLMEvalKit Data Storage Environment
- Environment:Truera Trulens LangChain LangGraph Environment
- Environment:Bentoml BentoML BentoCloud Credentials