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:Norrrrrrr lyn WAInjectBench Image Prompt Injection Detection
- Workflow:Apache Hudi Docker Demo Setup
- Workflow:Vllm project Vllm Multi LoRA Serving
- Workflow:Treeverse LakeFS Data Version Control With Branches
- Workflow:Microsoft BIPIA Black Box Defense Evaluation
- Workflow:Sgl project Sglang ModelOpt Quantization And Export
- Workflow:Apache Shardingsphere Metadata DDL Refresh
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Translation
- Workflow:Trailofbits Fickling Pickle Safety Analysis
- Workflow:Open compass VLMEvalKit API Model Evaluation
Principles
- Principle:Intel Ipex llm LISA Dynamic Layer Training
- Principle:Tensorflow Tfjs Define Model Architecture
- Principle:Mistralai Client python Streaming Chat Completion
- Principle:Protectai Modelscan Model File Abstraction
- Principle:Diagram of thought Diagram of thought Convergence Assessment
- Principle:DistrictDataLabs Yellowbrick Bestfit Regression Overlay
- Principle:Volcengine Verl VLM Model Configuration
- Principle:Bitsandbytes foundation Bitsandbytes Matmul Performance Estimation
- Principle:FlowiseAI Flowise User Profile Management
- Principle:Datajuicer Data juicer QA Calibration
Implementations
- Implementation:BerriAI Litellm Literal AI Logger
- Implementation:Hiyouga LLaMA Factory WebUI Runner
- Implementation:Ggml org Ggml Mnist model init random
- Implementation:Google deepmind Dm control Walker Info
- Implementation:Astronomer Astronomer cosmos Provider Info
- Implementation:Microsoft Playwright WkPage
- Implementation:Ollama Ollama Llama Graph
- Implementation:Kubeflow Kubeflow Istio Certmanager Dex Setup
- Implementation:Elevenlabs Elevenlabs python ConversationalConfigApiModelWorkflowOverrideOutput
- Implementation:Arize ai Phoenix Legacy GeminiModel
Heuristics
- Heuristic:Lance format Lance Vector Index Tuning
- Heuristic:CARLA simulator Carla Traffic Manager Sync Mode
- Heuristic:Google research Deduplicate text datasets Variable Width Pointer Optimization
- Heuristic:Deepspeedai DeepSpeed ZeRO Pipeline Incompatibility
- Heuristic:Webdriverio Webdriverio Stale Element Auto Refetch
- Heuristic:Mage ai Mage ai HTTP Error Classification
- Heuristic:Facebookresearch Audiocraft Codebook Dead Code Expiration
- Heuristic:LLMBook zh LLMBook zh github io Deduplication Ngram Threshold
- Heuristic:Openclaw Openclaw Config Cascade Resolution
- Heuristic:SeldonIO Seldon core Autoscaling Dual Config Tip
Environments
- Environment:SqueezeAILab ETS Evaluation Python Stack
- Environment:InternLM Lmdeploy Build From Source
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Datahub project Datahub Spark Lineage Environment
- Environment:Vespa engine Vespa Java 17 Build Runtime
- Environment:ClickHouse ClickHouse CI Docker Environment
- Environment:Protectai Modelscan H5py Optional
- Environment:Microsoft Onnxruntime Sklearn Conversion Environment
- Environment:Ray project Ray Java Build Environment
- Environment:Volcengine Verl vLLM Rollout Environment