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:Puppeteer Puppeteer Web Scraping And Interaction
- Workflow:Tensorflow Tfjs GPT2 Text Generation
- Workflow:NVIDIA NeMo Curator Semantic Deduplication
- Workflow:Roboflow Rf detr Object Detection Inference
- Workflow:Nightwatchjs Nightwatch Custom Commands And Assertions
- Workflow:Bentoml BentoML Service Definition And Local Serving
- Workflow:Helicone Helicone Integrate Provider To Gateway
- Workflow:Apache Dolphinscheduler Datasource Plugin Development
- Workflow:Neuml Txtai Workflow Orchestration
- Workflow:Microsoft Autogen Tool Augmented Agent
Principles
- Principle:Heibaiying BigData Notes Flink Streaming Environment
- Principle:Microsoft DeepSpeedExamples ZeRO Stage3 Initialization
- Principle:Lm sys FastChat MT Bench Answer Generation
- Principle:InternLM Lmdeploy W8A8 Quantized Inference
- Principle:Microsoft Agent framework Magentic Orchestration Pattern
- Principle:Microsoft Onnxruntime Model Conversion to ONNX
- Principle:Togethercomputer Together python Client Initialization
- Principle:Ollama Ollama Llama Cpp Common Library
- Principle:Huggingface Diffusers Scheduler Selection
- Principle:Lm sys FastChat MT Bench Result Display
Implementations
- Implementation:Speechbrain Speechbrain Prepare ESC50
- Implementation:Haifengl Smile PerfectHash
- Implementation:CARLA simulator Carla Python LightManager Bindings
- Implementation:Nightwatchjs Nightwatch Page Object Type Definitions
- Implementation:Hpcaitech ColossalAI Code Reward Testing Util
- Implementation:Microsoft Autogen DiGraph Model
- Implementation:Microsoft Onnxruntime Torch NN Module Construction
- Implementation:Langgenius Dify UpdateAppApiStatus
- Implementation:DistrictDataLabs Yellowbrick ConfusionMatrix Visualizer
- Implementation:FlowiseAI Flowise GetEvaluation
Heuristics
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:Huggingface Transformers FSDP Activation Checkpointing Tip
- Heuristic:Apache Spark Memory Tuning Tips
- Heuristic:Gretelai Gretel synthetics Parallel Generation CUDA Disable
- Heuristic:Spotify Luigi PySpark Task Serialization
- Heuristic:Spcl Graph of thoughts Backoff Retry On API Errors
- Heuristic:Ggml org Llama cpp Batch Size BLAS Minimum
- Heuristic:Mage ai Mage ai Sorted Data Bookmark Strategy
- Heuristic:Deepspeedai DeepSpeed Shared Memory Sizing
- Heuristic:CarperAI Trlx Delta Rewards
Environments
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:Junyanz Pytorch CycleGAN and pix2pix DDP Multi GPU
- Environment:Teamcapybara Capybara Ruby And Gem Dependencies
- Environment:Openai Evals OpenAI API Configuration
- Environment:Datahub project Datahub Frontend Build
- Environment:Google deepmind Dm control EGL Headless Rendering
- Environment:Vllm project Vllm Environment Variables
- Environment:HKUDS AI Trader MCP Services
- Environment:Lakeraai Pint benchmark Python 310 With Transformers
- Environment:Dotnet Machinelearning Platform Architecture Support