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:Googleapis Python genai Function Calling and Tools
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:Roboflow Rf detr ONNX Export
- Workflow:Sdv dev SDV Sequential data synthesis
- Workflow:Openai Openai node Chat Completion
- Workflow:Mage ai Mage ai Building a New Destination Connector
- Workflow:Junyanz Pytorch CycleGAN and pix2pix Pretrained Inference
- Workflow:Cypress io Cypress Project Setup and Configuration
- Workflow:Lance format Lance Table Optimization
- Workflow:DataTalksClub Data engineering zoomcamp dlt Data Ingestion
Principles
- Principle:Tensorflow Serving Static Path Source
- Principle:PrefectHQ Prefect Worker Configuration
- Principle:Iterative Dvc Stage Freshness Detection
- Principle:Mistralai Client python Streaming Chat Completion
- Principle:Scikit learn Scikit learn Kernel Methods
- Principle:LaurentMazare Tch rs SGD Optimization
- Principle:Apache Druid Schema Discovery
- Principle:Haotian liu LLaVA Conversation Prompt Construction
- Principle:Google deepmind Mujoco JIT Compilation
- Principle:Ollama Ollama ModelArchitecture
Implementations
- Implementation:Online ml River Datasets Taxis
- Implementation:Ucbepic Docetl ExperimentSimpleAgent
- Implementation:Langgenius Dify UsePay
- Implementation:LLMBook zh LLMBook zh github io Apply Rotary Pos Emb
- Implementation:Hpcaitech ColossalAI Model Utils
- Implementation:Kornia Kornia Accuracy Metric
- Implementation:Openai Evals AnthropicSolver
- Implementation:Mage ai Mage ai Azure Blob Storage Source
- Implementation:Apache Druid Docusaurus Site Config
- Implementation:Datahub project Datahub SchemaTronDataHubType
Heuristics
- Heuristic:Hiyouga LLaMA Factory Quantized Training Best Practices
- Heuristic:Lance format Lance Encoding Compression Thresholds
- Heuristic:Romsto Speculative Decoding KV Cache Instability
- Heuristic:Vllm project Vllm Batch Size Hardware Scaling
- Heuristic:Iamhankai Forest of Thought Input Length Overflow Recovery
- Heuristic:Microsoft BIPIA LLAMA Pad Token Workaround
- Heuristic:Google deepmind Mujoco Mesh Quality For Collision
- Heuristic:Anthropics Anthropic sdk python Adaptive Thinking Over Enabled
- Heuristic:Danijar Dreamerv3 Free Nats KL Thresholding
- Heuristic:HKUDS AI Trader Sortino Ratio Capping
Environments
- Environment:BerriAI Litellm Provider API Credentials
- Environment:Ggml org Ggml Metal GPU Environment
- Environment:Teamcapybara Capybara Ruby And Gem Dependencies
- Environment:Sgl project Sglang CUDA SM100
- Environment:Mlc ai Web llm WebGPU Browser Runtime
- Environment:Huggingface Alignment handbook Python TRL
- Environment:Mage ai Mage ai Singer SDK And Joblib Runtime
- Environment:Openai Openai python Python 3 9 Plus
- Environment:Alibaba ROLL ROCm GPU Environment
- Environment:HKUDS AI Trader Browser Runtime