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:Onnx Onnx Model Validation
- Workflow:Deepseek ai Janus Multimodal Understanding
- Workflow:Mit han lab Llm awq TinyChat LLM Deployment
- Workflow:Openclaw Openclaw Gateway Operations And Diagnostics
- Workflow:LLMBook zh LLMBook zh github io DPO Alignment
- Workflow:HKUDS AI Trader Data Pipeline
- Workflow:Scikit learn contrib Imbalanced learn Balanced Deep Learning Training
- Workflow:Turboderp org Exllamav2 LoRA Adapter Inference
- Workflow:Hiyouga LLaMA Factory Model Export and Merging
- Workflow:OpenGVLab InternVL Supervised Finetuning
Principles
- Principle:Promptfoo Promptfoo Assertion Grading
- Principle:Togethercomputer Together python Fine Tuning Job Monitoring
- Principle:DistrictDataLabs Yellowbrick Missing Data Visualization
- Principle:Triton inference server Server Signal Handling
- Principle:Truera Trulens Feedback Function Definition
- Principle:Ggml org Llama cpp Debugging
- Principle:HKUDS AI Trader Frontend Configuration Loading
- Principle:MaterializeInc Materialize Platform Check Pattern
- Principle:EvolvingLMMs Lab Lmms eval Metric Definition
- Principle:Langchain ai Langchain Streaming Events
Implementations
- Implementation:Zai org CogVideo Caption Load Video
- Implementation:Explodinggradients Ragas AgentGoalAccuracy Metric
- Implementation:Nautechsystems Nautilus trader TestInstrumentProvider Factory
- Implementation:Google deepmind Dm control MuJoCo Profiling Wrapper
- Implementation:Sdv dev SDV Metadata Load From Json
- Implementation:NVIDIA TransformerEngine JAX XLA Attention
- Implementation:Turboderp org Exllamav2 ExLlamaV2DynamicGeneratorAsync
- Implementation:OpenHands OpenHands DeviceCodeStore
- Implementation:Fede1024 Rust rdkafka Producer Transaction Methods
- Implementation:Microsoft Onnxruntime CUDA AdamW
Heuristics
- Heuristic:Arize ai Phoenix Queue Clear Race Condition
- Heuristic:Apache Flink Async Sink Timeout And Backpressure Defaults
- Heuristic:Microsoft BIPIA Torch Compile Platform Guard
- Heuristic:Apache Spark Partition Sizing Tips
- Heuristic:Neuml Txtai Thread Safety Constraints
- Heuristic:Turboderp org Exllamav2 Paged Cache Configuration
- Heuristic:SqueezeAILab ETS Softmax Temperature Tuning
- Heuristic:DistrictDataLabs Yellowbrick Scikit Learn API Compatibility
- Heuristic:Microsoft Agent framework Function Invocation Defaults
- Heuristic:Openai Whisper Compression Ratio Threshold
Environments
- Environment:Microsoft Agent framework Python 3 10 Runtime
- Environment:Microsoft Playwright Platform Support Environment
- Environment:Ucbepic Docetl LLM API Keys
- Environment:TobikoData Sqlmesh GitHub CICD Runner
- Environment:Turboderp org Exllamav2 CUDA GPU Runtime
- Environment:Microsoft BIPIA OpenAI API Environment
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:Apache Shardingsphere Etcd Cluster Coordination
- Environment:SeleniumHQ Selenium Grid Deployment Environment
- Environment:DataTalksClub Data engineering zoomcamp Docker PostgreSQL Python Environment