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:Puppeteer Puppeteer Page Screenshot Capture
- Workflow:SeleniumHQ Selenium Page Object Pattern Testing
- Workflow:Openai CLIP Zero shot image classification
- Workflow:Microsoft Onnxruntime Python Inference Pipeline
- Workflow:Sail sg LongSpec Speculative Decoding Inference
- Workflow:Huggingface Transformers PEFT Adapter Integration
- Workflow:Lance format Lance Vector Search Pipeline
- Workflow:Haifengl Smile Model Serving Pipeline
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Run llama Llama index Embedding Finetuning
Principles
- Principle:Huggingface Diffusers ControlNet Residual Injection
- Principle:Apache Druid Tuning Parameters
- Principle:Shiyu coder Kronos Sequential Two Stage Training
- Principle:TobikoData Sqlmesh Plan Creation And Change Detection
- Principle:AUTOMATIC1111 Stable diffusion webui Extension Callback System
- Principle:Online ml River Online Nearest Neighbors
- Principle:Huggingface Diffusers LoRA Export
- Principle:Fede1024 Rust rdkafka Mock Client Configuration
- Principle:ContextualAI HALOs Data Preparation
- Principle:Huggingface Datasets Distributed Dataset Splitting
Implementations
- Implementation:Predibase Lorax LoRA Weights Load
- Implementation:Openai Openai python Function Tool Param
- Implementation:Mlc ai Mlc llm Error Protocol
- Implementation:Online ml River Optim Losses
- Implementation:OWASP Www project top 10 for large language model applications VulnerabilityEntry Extract Prevention Strategies
- Implementation:ARISE Initiative Robosuite MobileBaseController Base
- Implementation:Astronomer Astronomer cosmos TrinoLDAPProfileMapping
- Implementation:Allenai Open instruct SFTDatasetProcessor
- Implementation:FlagOpen FlagEmbedding VideoChat2 Choice Bench
- Implementation:Googleapis Python genai Models Generate Content
Heuristics
- Heuristic:Tencent Ncnn Lightmode Memory Optimization
- Heuristic:Open compass VLMEvalKit Judge Model Selection By Dataset
- Heuristic:Sdv dev SDV Version Compatibility
- Heuristic:Liu00222 Open Prompt Injection BPE Retokenization Parameters
- Heuristic:Huggingface Datasets Cache Fingerprinting Tips
- Heuristic:Apache Druid Auto Granularity Selection
- Heuristic:Openai CLIP JIT Vs Non JIT Loading
- Heuristic:Apache Hudi Compaction Scheduling Safety
- Heuristic:Openai Openai node Warning Deprecated Beta Realtime
- Heuristic:EvolvingLMMs Lab Lmms eval Distributed Padding Strategy
Environments
- Environment:Zai org CogVideo Video Captioning Environment
- Environment:DataTalksClub Data engineering zoomcamp Dbt DuckDB Environment
- Environment:Googleapis Python genai Vertex AI Service Account
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:VainF Torch Pruning CUDA GPU Benchmarking
- Environment:Axolotl ai cloud Axolotl CUDA GPU
- Environment:Unslothai Unsloth Llama Cpp
- Environment:ArroyoSystems Arroyo Object Storage
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Run llama Llama index OpenAI API Configuration