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:Obss Sahi COCO Evaluation
- Workflow:Haosulab ManiSkill Imitation Learning Pipeline
- Workflow:Norrrrrrr lyn WAInjectBench Text Prompt Injection Detection
- Workflow:Ggml org Ggml MNIST Training And Evaluation
- Workflow:Risingwavelabs Risingwave Docker Deployment
- Workflow:Mlc ai Web llm Basic Chat Completion
- Workflow:Speechbrain Speechbrain CTC ASR Training
- Workflow:Googleapis Python genai Model Fine Tuning
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:Openclaw Openclaw Multi Agent Routing
Principles
- Principle:Googleapis Python genai Tool Configuration
- Principle:HKUDS AI Trader Agent Class Resolution
- Principle:Lm sys FastChat Environment Setup
- Principle:Nightwatchjs Nightwatch Component Test Authoring
- Principle:Deepseek ai Janus Conversation Formatting
- Principle:Huggingface Diffusers DreamBooth Dataset
- Principle:Gretelai Gretel synthetics DataFrame Upsampling
- Principle:NVIDIA NeMo Aligner SFT Data Preparation
- Principle:OWASP Www project top 10 for large language model applications Manual Adversarial Testing
- Principle:Allenai Open instruct Reward Extraction
Implementations
- Implementation:Apache Hudi ClusteringCommitSink DoCommit
- Implementation:Microsoft Autogen Studio Sidebar
- Implementation:Mlc ai Web llm Multi Model RAG Engine
- Implementation:SeleniumHQ Selenium CdpClientGenerator
- Implementation:CARLA simulator Carla World Apply Settings
- Implementation:Microsoft Autogen Studio Google Search Tool
- Implementation:CARLA simulator Carla RecurrentSharedFuture
- Implementation:Astronomer Astronomer cosmos Aws Ecs Operators
- Implementation:Run llama Llama index Node Recency Postprocessors
- Implementation:TobikoData Sqlmesh PlanChangePreview
Heuristics
- Heuristic:Haifengl Smile BFGS Convergence Tuning
- Heuristic:Mage ai Mage ai Parallel Sink Concurrency Limit
- Heuristic:ArroyoSystems Arroyo Batch Size And Backpressure
- Heuristic:Kornia Kornia Avoid Inplace Ops Compile
- Heuristic:Promptfoo Promptfoo Cache Configuration Tips
- Heuristic:Pytorch Serve Batch Size Tuning
- Heuristic:Lance format Lance Warning Deprecated Java APIs
- Heuristic:Lance format Lance Warning Deprecated Legacy Encodings
- Heuristic:LaurentMazare Tch rs MPS Weight Loading Workaround
- Heuristic:Apache Kafka Unknown Record Type Upgrade Safety
Environments
- Environment:DevExpress Testcafe Chrome Browser
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:LMCache LMCache CUDA GPU Runtime
- Environment:Vllm project Vllm CUDA Runtime
- Environment:Alibaba ROLL Ascend NPU Environment
- Environment:Haifengl Smile Java 25 Runtime
- Environment:Huggingface Datasets Python PyArrow Core
- Environment:Openai Openai python Voice Helpers
- Environment:Langchain ai Langgraph Docker Deployment Environment
- Environment:Huggingface Optimum Accelerated Inference Environment