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:NVIDIA NeMo Aligner REINFORCE Training
- Workflow:PacktPublishing LLM Engineers Handbook RAG Inference
- Workflow:Tensorflow Serving Batched Inference Pipeline
- Workflow:Datajuicer Data juicer Dataset Quality Analysis
- Workflow:Datahub project Datahub Java SDK Metadata Emission
- Workflow:Langchain ai Langchain Vector Store Operations
- Workflow:Nightwatchjs Nightwatch Custom Commands And Assertions
- Workflow:Google deepmind Mujoco GPU batched simulation MJX
- Workflow:Avdvg InjectGuard Vector Similarity Detection Pipeline
- Workflow:DevExpress Testcafe Basic Test Authoring
Principles
- Principle:Tensorflow Tfjs Training Data Preparation
- Principle:Vespa engine Vespa Initial Configuration Fetch
- Principle:Haotian liu LLaVA Conversation Prompt Construction
- Principle:Ggml org Llama cpp LoRA Adapter Acquisition
- Principle:Microsoft Autogen Tool Workbench
- Principle:Cohere ai Cohere python Embed Response Processing
- Principle:Huggingface Datatrove IPC Data Reading
- Principle:Lance format Lance Schema Evolution
- Principle:OpenHands OpenHands Solvability Analysis
- Principle:Snorkel team Snorkel Slice Performance Evaluation
Implementations
- Implementation:Ollama Ollama Llama Quant
- Implementation:Microsoft Playwright AndroidDispatcher
- Implementation:Avhz RustQuant ISIN
- Implementation:Volcengine Verl Split Placement Fit
- Implementation:MarketSquare Robotframework browser Babel Transpile
- Implementation:Sdv dev SDV Get Column Pair Plot
- Implementation:Avhz RustQuant FractionalProcess
- Implementation:DataTalksClub Data engineering zoomcamp Java JsonKStream
- Implementation:TobikoData Sqlmesh FileExplorer DragLayer
- Implementation:Run llama Llama index CustomLLM
Heuristics
- Heuristic:Apache Airflow Memory Management Tips
- Heuristic:Datahub project Datahub Batch Size And Timeout Tuning
- Heuristic:ChenghaoMou Text dedup SimHash Optimization Ceiling
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Batch Size One Default
- Heuristic:Wandb Weave Payload Size Limits
- Heuristic:Getgauge Taiko Element Actionability Checks
- Heuristic:Volcengine Verl Sequence Length Balancing
- Heuristic:Run llama Llama index Worker Count Configuration
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
- Heuristic:DevExpress Testcafe CDP Performance Monitoring
Environments
- Environment:Huggingface Trl PEFT LoRA Environment
- Environment:Tensorflow Serving Python Client Environment
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Unstructured IO Unstructured All Docs
- Environment:Astronomer Astronomer cosmos Kubernetes Provider
- Environment:OpenGVLab InternVL DeepSpeed
- Environment:Intel Ipex llm Windows Environment
- Environment:Huggingface Datasets Python PyArrow Core
- Environment:Google deepmind Dm control EGL Headless Rendering
- Environment:Openclaw Openclaw Node 22 Runtime