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:Teamcapybara Capybara Selenium Driver Configuration
- Workflow:LMCache LMCache CacheBlend KV Reuse
- Workflow:Deepspeedai DeepSpeed AutoTP Training
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:Cleanlab Cleanlab Datalab Dataset Audit
- Workflow:Huggingface Diffusers Checkpoint Conversion
- Workflow:CarperAI Trlx RLHF Dialogue Alignment
- Workflow:Bentoml BentoML Bento Build And Containerization
- Workflow:Openai CLIP Prompt engineered classification
Principles
- Principle:Ollama Ollama KVCache Causal Attention
- Principle:Cypress io Cypress Component Result Review
- Principle:Getgauge Taiko Page Screenshot
- Principle:Scikit learn contrib Imbalanced learn Package Initialization
- Principle:FlowiseAI Flowise Document Processing
- Principle:Dotnet Machinelearning Matrix Factorization
- Principle:ARISE Initiative Robosuite MJCF XML Manipulation
- Principle:Pyro ppl Pyro Posterior Predictive Analysis
- Principle:Roboflow Rf detr ONNX Runtime Validation
- Principle:Sktime Pytorch forecasting Hyperparameter Optimization
Implementations
- Implementation:Microsoft LoRA Legacy Run SWAG
- Implementation:Elevenlabs Elevenlabs python ChapterResponse
- Implementation:Online ml River Tree Splitter NominalReg
- Implementation:Apache Flink SourceReaderBase
- Implementation:Allenai Open instruct Beaker Experiment Workflow
- Implementation:Langgenius Dify Model Config Utils
- Implementation:Ollama Ollama Llama Common
- Implementation:Apache Shardingsphere HintShadowAlgorithm SPI
- Implementation:Microsoft Onnxruntime CPU GradientControl
- Implementation:Microsoft Onnxruntime OrtLoggingLevel
Heuristics
- Heuristic:Lm sys FastChat GPU Memory Allocation Strategy
- Heuristic:Trailofbits Fickling Allowlist Maintenance
- Heuristic:CrewAIInc CrewAI MCP Timeout And Retry Strategy
- Heuristic:Langfuse Langfuse LLM Rate Limit 24h Abandon
- Heuristic:Apache Paimon File Sizing and Split Planning
- Heuristic:PeterL1n BackgroundMattingV2 ONNX Patch Method Compatibility
- Heuristic:Deepspeedai DeepSpeed Sequence Parallel PyTorch Version
- Heuristic:Pyro ppl Pyro Enumeration Plate Nesting
- Heuristic:Openclaw Openclaw Config Cascade Resolution
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
Environments
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:VainF Torch Pruning CUDA GPU Benchmarking
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:Evidentlyai Evidently Spark Engine Environment
- Environment:Infiniflow Ragflow Docker Infrastructure
- Environment:Spotify Luigi AWS S3 Storage
- Environment:Rapidsai Cuml CUDA GPU
- Environment:Pytorch Serve vLLM Engine Environment
- Environment:Alibaba MNN Python Export Environment
- Environment:Tencent Ncnn Build Environment