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:Microsoft Playwright Browser automation CLI
- Workflow:Mlc ai Web llm Chrome Extension Integration
- Workflow:Avhz RustQuant Monte Carlo Option Pricing
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Recommenders team Recommenders Algorithm Benchmarking
- Workflow:Neuml Txtai RAG Pipeline
- Workflow:EvolvingLMMs Lab Lmms eval Distributed Multi GPU Evaluation
- Workflow:Apache Beam Portable Pipeline Submission
- Workflow:Cypress io Cypress CI Pipeline Integration
- Workflow:Microsoft Semantic kernel Vector Store RAG Pipeline
Principles
- Principle:FlowiseAI Flowise Dependency Management
- Principle:TobikoData Sqlmesh Macro And Jinja Translation
- Principle:ARISE Initiative Robosuite Robot Base Model Design
- Principle:Ggml org Llama cpp Template Capability Detection
- Principle:Datahub project Datahub CLI Package Installation
- Principle:Facebookresearch Audiocraft Audio Tokenizer Selection
- Principle:Heibaiying BigData Notes HBase Data Deletion
- Principle:InternLM Lmdeploy Backend Auto Selection
- Principle:Openai Whisper Evaluation Benchmarking
- Principle:Webdriverio Webdriverio Selector Processing
Implementations
- Implementation:Huggingface Datasets Dataset Select
- Implementation:Sgl project Sglang CPU QKV Projection
- Implementation:Haosulab ManiSkill AllegroHand
- Implementation:Mistralai Client python Azure ChatCompletionStreamRequest
- Implementation:Huggingface Datatrove TextUtils
- Implementation:Apache Druid SampleForConnect
- Implementation:Avhz RustQuant Python Bindings
- Implementation:ChenghaoMou Text dedup SimHash Check False Positives
- Implementation:Ucbepic Docetl Directive ReduceChaining
- Implementation:Scikit learn Scikit learn PCA
Heuristics
- Heuristic:Mbzuai oryx Awesome LLM Post training Reference Citation Cap 200
- Heuristic:DistrictDataLabs Yellowbrick NaN Data Handling
- Heuristic:PeterL1n BackgroundMattingV2 Data Augmentation Strategy
- Heuristic:Astronomer Astronomer cosmos Dbt Invocation Mode Selection
- Heuristic:Trailofbits Fickling Race Condition Prevention
- Heuristic:Vllm project Vllm Attention Backend Selection
- Heuristic:Huggingface Open r1 Distributed Training Configuration
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Ggml org Ggml Sampling Parameter Defaults
- Heuristic:Neuml Txtai LLM Context Window Fallback
Environments
- Environment:Evidentlyai Evidently Grafana Monitoring Environment
- Environment:Datahub project Datahub Docker Quickstart Environment
- Environment:Mlflow Mlflow Docker Container Environment
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Sgl project Sglang CUDA
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:OpenGVLab InternVL PyTorch CUDA
- Environment:Huggingface Open r1 CUDA Environment
- Environment:Openai Whisper PyTorch CUDA
- Environment:Zai org CogVideo Diffusers Inference Environment