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:Google deepmind Dm control Multi Agent Soccer Setup
- Workflow:Apache Hudi Flink Table Clustering
- Workflow:Onnx Onnx Model Creation
- Workflow:Risingwavelabs Risingwave Docker Deployment
- Workflow:Eventual Inc Daft Multimodal AI Batch Inference
- Workflow:Microsoft DeepSpeedExamples ZeRO Inference
- Workflow:Microsoft Agent framework Multi Agent Sequential Orchestration
- Workflow:FlagOpen FlagEmbedding Embedder Finetuning
- Workflow:Teamcapybara Capybara Element Finding And Interaction
- Workflow:Apache Kafka Coordinator Runtime Lifecycle
Principles
- Principle:Microsoft Agent framework Workflow Result Processing
- Principle:Webdriverio Webdriverio Environment Detection
- Principle:Run llama Llama index Training Data Validation
- Principle:Kubeflow Kubeflow Development And Testing
- Principle:Onnx Onnx Opset Version Mapping
- Principle:Heibaiying BigData Notes Storm Spout Implementation
- Principle:Openai Openai node Audio Translation
- Principle:Huggingface Datatrove Unigram Log Probability Filtering
- Principle:Apache Beam Execution Monitoring
- Principle:Allenai Open instruct Human Evaluation
Implementations
- Implementation:Open compass VLMEvalKit WorldSense Utils
- Implementation:VainF Torch Pruning BasePruner
- Implementation:Promptfoo Promptfoo GitHub Action
- Implementation:Risingwavelabs Risingwave Relations Component
- Implementation:Elevenlabs Elevenlabs python GetKnowledgeBaseFileResponseModel
- Implementation:Hpcaitech ColossalAI Booster Training Loop
- Implementation:Haotian liu LLaVA Make Delta
- Implementation:Getgauge Taiko DropDown Select
- Implementation:FlowiseAI Flowise WorkspaceUsers
- Implementation:SeleniumHQ Selenium ModuleGenerator
Heuristics
- Heuristic:LLMBook zh LLMBook zh github io BF16 Mixed Precision Default
- Heuristic:Unslothai Unsloth Merge Memory Management
- Heuristic:Predibase Lorax Quantization Backend Selection
- Heuristic:Wandb Weave Payload Size Limits
- Heuristic:Marker Inc Korea AutoRAG Batch Size Tuning
- Heuristic:Pytorch Serve CPU Performance Tuning
- Heuristic:Kubeflow Kubeflow Kustomize Build Pipe Apply Pattern
- Heuristic:Fede1024 Rust rdkafka Multi Version Dependency Hazard
- Heuristic:Danijar Dreamerv3 Free Nats KL Thresholding
- Heuristic:EvolvingLMMs Lab Lmms eval Bootstrap Iteration Optimization
Environments
- Environment:Datahub project Datahub Spark Lineage Environment
- Environment:Apache Airflow Database Backend Environment
- Environment:Apache Druid Web Console Development
- Environment:Pyro ppl Pyro Visualization Tools
- Environment:Vllm project Vllm Intel XPU
- Environment:Predibase Lorax Python Server Dependencies
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Obss Sahi Python Detection Frameworks
- Environment:Vllm project Vllm Python
- Environment:OpenBMB UltraFeedback OpenAI API Environment