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:HKUDS AI Trader Multi Agent Comparison
- Workflow:ARISE Initiative Robomimic Hyperparameter Sweep
- Workflow:Openai Openai node Streaming To Client
- Workflow:Sdv dev SDV Single table synthesis
- Workflow:PrefectHQ Prefect Database Cleanup With Approval
- Workflow:Avhz RustQuant Yield Curve Construction
- Workflow:Microsoft Agent framework Multi Agent Sequential Orchestration
- Workflow:Shiyu coder Kronos Single Series Prediction
- Workflow:Facebookresearch Habitat lab Rearrangement HRL Training
- Workflow:Explodinggradients Ragas Metric Prompt Optimization
Principles
- Principle:Triton inference server Server Generate API
- Principle:Cleanlab Cleanlab Confident Joint Estimation
- Principle:Kornia Kornia ONNX Inference
- Principle:Huggingface Datasets Abstract Dataset IO
- Principle:Google deepmind Mujoco Binary Model Loading
- Principle:Treeverse LakeFS Merge
- Principle:Openai Openai python Structured Output Definition
- Principle:LLMBook zh LLMBook zh github io Loss Masking Tokenization
- Principle:Speechbrain Speechbrain Brain Subclass Initialization
- Principle:Haifengl Smile SQL Data Ingestion
Implementations
- Implementation:Anthropics Anthropic sdk python Core Types
- Implementation:Tensorflow Tfjs Tf LoadLayersModel For Transfer
- Implementation:NVIDIA DALI Fn Crop Mirror Normalize
- Implementation:Zai org CogVideo SAT Get Args
- Implementation:Microsoft Playwright TraceV7
- Implementation:Langfuse Langfuse Dashboards Repository
- Implementation:Haosulab ManiSkill RecordEpisode Wrapper
- Implementation:BerriAI Litellm Get Llm Provider
- Implementation:Vllm project Vllm SM100 FMHA MLA Reduction
- Implementation:Online ml River Stats AutoCorr
Heuristics
- Heuristic:Snorkel team Snorkel Precision Init Prior
- Heuristic:PrefectHQ Prefect Concurrency Limit Scoping
- Heuristic:Predibase Lorax CUDA Graph Batch Size Caching
- Heuristic:Vibrantlabsai Ragas Analytics Silent Failure Pattern
- Heuristic:NVIDIA NeMo Curator GPU Memory Resource Allocation
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Deepset ai Haystack Pipeline Deep Copy Safety
- Heuristic:Cypress io Cypress Xvfb Display Gotcha
- Heuristic:Protectai Llm guard Token Limit Early Guard
- Heuristic:DataExpert io Data engineer handbook Watermark Late Arrival Tolerance
Environments
- Environment:ArroyoSystems Arroyo Webui Runtime
- Environment:Sgl project Sglang OpenAI
- Environment:Lm sys FastChat SFT Training Environment
- Environment:Protectai Llm guard API Server Deployment
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:Mlc ai Mlc llm Metal macOS iOS Environment
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Sktime Pytorch forecasting Matplotlib Plotting Dependencies
- Environment:Volcengine Verl Megatron Core Environment
- Environment:Snorkel team Snorkel Dask Distributed