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:Langgenius Dify Plugin Management
- Workflow:Haifengl Smile Nearest Neighbor Search
- Workflow:CARLA simulator Carla Sensor Data Collection
- Workflow:Confident ai Deepeval End to End LLM Evaluation
- Workflow:Confident ai Deepeval AI Agent Evaluation
- Workflow:Speechbrain Speechbrain Speech Enhancement Training
- Workflow:Zai org CogVideo Video Editing DDIM Inversion
- Workflow:Rapidsai Cuml Sklearn Zero Code Acceleration
- Workflow:FMInference FlexLLMGen HELM Benchmark Evaluation
- Workflow:Intel Ipex llm vLLM Serving
Principles
- Principle:Langgenius Dify Model Configuration
- Principle:OpenRLHF OpenRLHF KTO Training
- Principle:Cleanlab Cleanlab Datalab Regression Label Issue Detection
- Principle:Spcl Graph of thoughts Graph of Operations Construction
- Principle:Microsoft BIPIA Prompt Construction With Defense
- Principle:Iterative Dvc Artifact Resolution
- Principle:Promptfoo Promptfoo Build And Packaging
- Principle:Nightwatchjs Nightwatch Element And Section Mapping
- Principle:Iamhankai Forest of Thought Forest of Thought Orchestration
- Principle:Treeverse LakeFS Hook Triggered Commit
Implementations
- Implementation:AUTOMATIC1111 Stable diffusion webui Model Loader
- Implementation:Neuml Txtai SQLite ANN
- Implementation:Pytorch Serve GptHandler
- Implementation:Microsoft Playwright WkProvisionalPage
- Implementation:Microsoft LoRA Style Doc
- Implementation:Rapidsai Cuml Breast Cancer Dataset
- Implementation:PacktPublishing LLM Engineers Handbook SFTTrainer Train
- Implementation:Nautechsystems Nautilus trader TradingNode Add Client Factory
- Implementation:MaterializeInc Materialize Util Module
- Implementation:PacktPublishing LLM Engineers Handbook HuggingFaceProcessor Run
Heuristics
- Heuristic:Sgl project Sglang Attention Backend Selection
- Heuristic:Datahub project Datahub Validation Cross API
- Heuristic:Astronomer Astronomer cosmos Cache Strategy Optimization
- Heuristic:Mlc ai Web llm Tokenizer JSON Preference
- Heuristic:Huggingface Optimum Dummy Input Shape Defaults
- Heuristic:Openai CLIP Class Name Curation
- Heuristic:Mlc ai Web llm Grammar Matcher Reuse
- Heuristic:Kubeflow Kubeflow Stale Issue Lifecycle Management
- Heuristic:Zai org CogVideo Data Preparation Best Practices
- Heuristic:Nightwatchjs Nightwatch Safari Parallel Limitation
Environments
- Environment:Promptfoo Promptfoo SQLite Database
- Environment:Eventual Inc Daft Ray Distributed Runner
- Environment:Hpcaitech ColossalAI CUDA GPU Environment
- Environment:Allenai Open instruct Beaker Cluster
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:FMInference FlexLLMGen NVMe Disk
- Environment:Openai Whisper FFmpeg
- Environment:Lance format Lance SIMD And Platform Requirements
- Environment:Iterative Dvc Git SCM Environment
- Environment:Vespa engine Vespa FNET Transport Config