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:Run llama Llama index Embedding Finetuning
- Workflow:Tensorflow Serving REST API Inference
- Workflow:Vllm project Vllm Speculative Decoding
- Workflow:Apache Kafka Coordinator Runtime Lifecycle
- Workflow:Onnx Onnx Model Validation
- Workflow:Norrrrrrr lyn WAInjectBench LLaVA Finetuning
- Workflow:Getgauge Taiko Interactive Test Recording
- Workflow:Kubeflow Kubeflow AI Lifecycle Pipeline
- Workflow:Puppeteer Puppeteer Request Interception
- Workflow:Promptfoo Promptfoo CI CD Integration
Principles
- Principle:Dagster io Dagster Dbt Test To Asset Check
- Principle:Helicone Helicone Payment Processing
- Principle:FlowiseAI Flowise Docker Deployment
- Principle:Intel Ipex llm DPO Model Export
- Principle:Ollama Ollama ImageGeneration
- Principle:Neuml Txtai Benchmark Evaluation
- Principle:Webdriverio Webdriverio Utility Functions
- Principle:Cleanlab Cleanlab Confident Joint Estimation
- Principle:Interpretml Interpret Classification Performance Curves
- Principle:Huggingface Datasets Download Configuration
Implementations
- Implementation:Microsoft Playwright TraceV8
- Implementation:Getgauge Taiko TextBox Element
- Implementation:CrewAIInc CrewAI XML Search Tool
- Implementation:NVIDIA DALI DALIClassificationIterator
- Implementation:Langgenius Dify Service Common
- Implementation:Datajuicer Data juicer TextChunkMapper
- Implementation:Lucidrains X transformers TransformerWrapper Decoder Init
- Implementation:FlowiseAI Flowise Typography
- Implementation:Infiniflow Ragflow FilesTable Component
- Implementation:Haosulab ManiSkill SimConfig
Heuristics
- Heuristic:Ggml org Llama cpp Warning Deprecated Legacy Converters
- Heuristic:Intel Ipex llm Llama Padding Token Workaround
- Heuristic:Langgenius Dify Token Refresh Loop Prevention
- Heuristic:Datahub project Datahub Validation Cross API
- Heuristic:OpenGVLab InternVL Dynamic Resolution Tiling
- Heuristic:Cypress io Cypress V8 Snapshot Memory
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:Protectai Modelscan Nested Zip Not Supported
- Heuristic:Sail sg LongSpec Tree Shape Configuration
Environments
- Environment:Facebookresearch Audiocraft Python PyTorch CUDA Environment
- Environment:Volcengine Verl CUDA GPU Environment
- Environment:Intel Ipex llm RAG LangChain Environment
- Environment:Obss Sahi Python Image Processing
- Environment:Huggingface Open r1 CUDA Environment
- Environment:Rapidsai Cuml Python RAPIDS Stack
- Environment:LMCache LMCache NIXL Transfer Library
- Environment:Spotify Luigi AWS S3 Storage
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:FMInference FlexLLMGen CUDA GPU