Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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 Creation
- Workflow:Hpcaitech ColossalAI DPO Alignment
- Workflow:Turboderp org Exllamav2 Multimodal Vision Inference
- Workflow:Googleapis Python genai Function Calling and Tools
- Workflow:Mlc ai Web llm Structured Output Generation
- Workflow:Cleanlab Cleanlab Classification Label Issue Detection
- Workflow:Elevenlabs Elevenlabs python Voice Cloning
- Workflow:Openai Openai python Chat Completion
- Workflow:LLMBook zh LLMBook zh github io Inference and Quantization
- Workflow:MarketSquare Robotframework browser Plugin Development
Principles
- Principle:Ggml org Llama cpp BatchProcessing
- Principle:OpenRLHF OpenRLHF Agent Based Rollout Collection
- Principle:PeterL1n BackgroundMattingV2 Image dataset loading
- Principle:Apache Druid Query Execution
- Principle:Speechbrain Speechbrain Perceptual Quality Evaluation
- Principle:Huggingface Datatrove Tokenized Dataset Loading
- Principle:Google deepmind Mujoco Quasi Random Sequences
- Principle:Microsoft Agent framework Agent Executor Wrapping
- Principle:Puppeteer Puppeteer Platform Detection
- Principle:SeldonIO Seldon core Usage Metrics Publishing
Implementations
- Implementation:Explodinggradients Ragas LangSmith Integration
- Implementation:Recommenders team Recommenders TF Utils
- Implementation:Sgl project Sglang Get Model Loader
- Implementation:Explodinggradients Ragas ResponseRelevancy Metric
- Implementation:BerriAI Litellm Prompt Management Base
- Implementation:Onnx Onnx Checker Cpp API
- Implementation:Sgl project Sglang Sgl Function Decorator
- Implementation:FlowiseAI Flowise SuggestionOption
- Implementation:Openai Openai python Tool Choice MCP
- Implementation:Microsoft DeepSpeedExamples BingBert TuringSources
Heuristics
- Heuristic:Datahub project Datahub Docker Memory Preflight
- Heuristic:NVIDIA NeMo Aligner DPO Sequence Packing Tips
- Heuristic:Apache Paimon Vector Index Configuration Tips
- Heuristic:ARISE Initiative Robomimic BatchNorm To GroupNorm For EMA
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Neuml Txtai MacOS Stability Workarounds
- Heuristic:Sktime Pytorch forecasting Target Normalization Transforms
- Heuristic:Apache Kafka Log4j Migration Compatibility
- Heuristic:Astronomer Astronomer cosmos Dbt Invocation Mode Selection
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
Environments
- Environment:Dagster io Dagster DAGSTER HOME Configuration
- Environment:Lm sys FastChat LoRA QLoRA Training Environment
- Environment:Huggingface Diffusers Training Environment
- Environment:Tencent Ncnn PyTorch Environment
- Environment:Openai Evals Optional Provider APIs
- Environment:Apache Beam Dataflow Streaming Runtime
- Environment:Huggingface Datatrove Python Runtime
- Environment:Tensorflow Tfjs Node Native Runtime
- Environment:Norrrrrrr lyn WAInjectBench OpenAI API Credentials
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies