Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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 node Fine Tuning
- Workflow:Apache Hudi Docker Demo Setup
- Workflow:Langgenius Dify Knowledge Base Creation
- Workflow:Langchain ai Langgraph ReAct Agent Creation
- Workflow:Scikit learn contrib Imbalanced learn SMOTE Resampling Pipeline
- Workflow:Helicone Helicone LLM Response Normalization
- Workflow:Haosulab ManiSkill Sim2Real Deployment
- Workflow:Togethercomputer Together python Embeddings And Reranking
- Workflow:Langfuse Langfuse Dataset experiment pipeline
- Workflow:DistrictDataLabs Yellowbrick Model Selection and Tuning
Principles
- Principle:Vllm project Vllm Server Metrics Monitoring
- Principle:Ggml org Ggml Backend Interface
- Principle:ClickHouse ClickHouse Wide Integer Arithmetic
- Principle:Apache Flink File Enumeration and Splitting
- Principle:Ray project Ray Autoscaling And Monitoring
- Principle:TobikoData Sqlmesh Dbt Model Discovery And Mapping
- Principle:Tensorflow Tfjs Activation Functions
- Principle:Mage ai Mage ai Catalog Selection
- Principle:Truera Trulens Dashboard Tab Architecture
- Principle:TA Lib Ta lib python Abstract Function Execution
Implementations
- Implementation:Openai Openai node Checkpoint Permissions
- Implementation:Deepspeedai DeepSpeed CUDA Accelerator
- Implementation:Langchain ai Langgraph Runtime Class
- Implementation:CrewAIInc CrewAI ContextualAI Rerank Tool
- Implementation:Lucidrains X transformers NonAutoregressiveWrapper Init
- Implementation:Tencent Ncnn YOLOv4 Example
- Implementation:Speechbrain Speechbrain Load Hyperpyyaml
- Implementation:Pola rs Polars Upsample and Interpolate
- Implementation:Eric mitchell Direct preference optimization Preference Loss
- Implementation:SeleniumHQ Selenium HasFullPageScreenshot
Heuristics
- Heuristic:Recommenders team Recommenders SAR Cold Start Items
- Heuristic:Microsoft BIPIA LLAMA Pad Token Workaround
- Heuristic:Apache Flink Bin Packing Complexity Guard
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:Openai Openai agents python GPT 5 Reasoning Settings
- Heuristic:Lance format Lance Fragment Sizing Strategy
- Heuristic:Unstructured IO Unstructured Libmagic Filetype Accuracy
- Heuristic:OpenBMB UltraFeedback API Retry Strategy
- Heuristic:Speechbrain Speechbrain Score Normalization Tips
- Heuristic:Lucidrains X transformers Flash Attention Configuration
Environments
- Environment:Microsoft LoRA NLG Eval External Tools
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:Langgenius Dify Credentials And Env Vars
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:Eric mitchell Direct preference optimization HuggingFace Transformers
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Openclaw Openclaw State Directory And Credentials
- Environment:Ggml org Llama cpp CMake Build Environment
- Environment:Farama Foundation Gymnasium Video Recording Dependencies