Main Page
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:CARLA simulator Carla Building from Source
- Workflow:Duckdb Duckdb Source Amalgamation And Packaging
- Workflow:Openai Evals Running an eval set
- Workflow:CarperAI Trlx RLHF Dialogue Alignment
- Workflow:DataTalksClub Data engineering zoomcamp Kafka Stream Processing
- Workflow:Huggingface Datatrove Minhash Deduplication
- Workflow:Mlfoundations Open flamingo Model Creation And Inference
- Workflow:Cypress io Cypress Binary Build and Release
- Workflow:DataExpert io Data engineer handbook PySpark Job Testing
- Workflow:Hpcaitech ColossalAI LLaMA Continual Pretraining
Principles
- Principle:PeterL1n BackgroundMattingV2 Video output writing
- Principle:Nightwatchjs Nightwatch Feature File Authoring
- Principle:Vllm project Vllm Multimodal Generation
- Principle:Neuml Txtai Word Embedding Vectorization
- Principle:Protectai Llm guard Prompt Injection Detection
- Principle:Arize ai Phoenix Experiment Evaluator Definition
- Principle:SeleniumHQ Selenium PageFactory Initialization
- Principle:Mit han lab Llm awq AWQ HuggingFace Export
- Principle:Vllm project Vllm Output Processing
- Principle:Obss Sahi COCO Dataset Slicing
Implementations
- Implementation:Google deepmind Mujoco Simulate Header
- Implementation:Scikit learn Scikit learn SpectralEmbedding
- Implementation:Openai Openai node Eval Runs Resource
- Implementation:SeldonIO Seldon core Seldon Model Infer
- Implementation:Openai Openai python Shared Params Reasoning
- Implementation:Deepseek ai Janus Apply Sft Template
- Implementation:Roboflow Rf detr RFDETR Init
- Implementation:Facebookresearch Audiocraft NoiseSchedule
- Implementation:Google deepmind Mujoco Engine IO Header
- Implementation:Microsoft Autogen ChatAgentContainer
Heuristics
- Heuristic:Microsoft LoRA LoRA Rank Selection
- Heuristic:DataTalksClub Data engineering zoomcamp DuckDB OOM Memory Management
- Heuristic:Recommenders team Recommenders SAR Cold Start Items
- Heuristic:Neuml Txtai Batch Size Defaults
- Heuristic:Onnx Onnx Shape Inference Limitations
- Heuristic:CARLA simulator Carla Synchronous Mode Fixed Delta
- Heuristic:Vespa engine Vespa Warning Deprecated Cloud API Constructors
- Heuristic:Datajuicer Data juicer Batch Size Adaptation
- Heuristic:Apache Beam Thread Pool Parallelism Sizing
- Heuristic:Haotian liu LLaVA Flash Attention GPU Requirement
Environments
- Environment:Neuml Txtai GPU Accelerator Environment
- Environment:Trailofbits Fickling Python Runtime
- Environment:Tensorflow Tfjs Browser Runtime
- Environment:Lance format Lance SIMD And Platform Requirements
- Environment:Openai Whisper FFmpeg
- Environment:Deepspeedai DeepSpeed NVMe Environment
- Environment:Openai Openai node Node 20 Runtime
- Environment:Googleapis Python genai Python 3 10 SDK Runtime
- Environment:Microsoft Semantic kernel DotNet SDK Environment
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack