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:Microsoft Agent framework Declarative Agent Definition
- Workflow:Anthropics Anthropic sdk python Basic Message Conversation
- Workflow:Openai Openai agents python Guardrails Secured Agent
- Workflow:Fastai Fastbook Image Classification
- Workflow:Explodinggradients Ragas RAG Evaluation
- Workflow:Dagster io Dagster Modal Serverless Pipeline
- Workflow:Neuml Txtai Semantic Search Pipeline
- Workflow:Openai CLIP Prompt engineered classification
- Workflow:Langfuse Langfuse Otel ingestion pipeline
- Workflow:FlagOpen FlagEmbedding Benchmark Evaluation
Principles
- Principle:Alibaba MNN Neural Network Inference
- Principle:Hiyouga LLaMA Factory Supervised Fine Tuning
- Principle:Junyanz Pytorch CycleGAN and pix2pix Pretrained Model Download
- Principle:Hpcaitech ColossalAI Benchmark Metric Computation
- Principle:OpenHands OpenHands Sandbox Command Execution
- Principle:Huggingface Diffusers Prior Preservation
- Principle:Microsoft Onnxruntime ONNX Input Schema Definition
- Principle:AnswerDotAI RAGatouille Model Training
- Principle:Liu00222 Open Prompt Injection Input Preprocessing
- Principle:FMInference FlexLLMGen HELM Batch Construction
Implementations
- Implementation:Ollama Ollama Format Time
- Implementation:SeleniumHQ Selenium Router And LocalDistributor
- Implementation:Openai Openai python Shared Responses Model
- Implementation:Turboderp org Exllamav2 Sampling H
- Implementation:SeldonIO Seldon core Seldon Pipeline Load And Status
- Implementation:Microsoft Onnxruntime NodeInfo
- Implementation:ArroyoSystems Arroyo Kinesis Connector
- Implementation:Mlc ai Mlc llm Ministral3 Model
- Implementation:NVIDIA NeMo Curator DecoderUtils
- Implementation:Langgenius Dify UseCommon
Heuristics
- Heuristic:Openai Openai python Retry Backoff Strategy
- Heuristic:Protectai Modelscan Exit Code Conventions
- Heuristic:MaterializeInc Materialize CI Retry Strategies
- Heuristic:Interpretml Interpret Categorical Float Conversion Gotcha
- Heuristic:Cohere ai Cohere python HTTP Retry Backoff Strategy
- Heuristic:Microsoft Agent framework PowerFx Python Version Limit
- Heuristic:Scikit learn contrib Imbalanced learn KNeighbors Selection Tips
- Heuristic:Bigscience workshop Petals Batch Splitting Threshold
- Heuristic:Risingwavelabs Risingwave Stream Chunk Sizing
- Heuristic:Dagster io Dagster Retry Strategy Configuration
Environments
- Environment:PacktPublishing LLM Engineers Handbook Unsloth Finetuning Environment
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies
- Environment:Microsoft Playwright Platform Support Environment
- Environment:Getgauge Taiko Linux System Libraries
- Environment:NVIDIA NeMo Aligner NeMo Framework GPU Environment
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:Alibaba MNN HuggingFace Ecosystem Environment
- Environment:Kserve Kserve Leader Worker Set
- Environment:Cohere ai Cohere python Python SDK Runtime
- Environment:Predibase Lorax Model Source Credentials