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:Rapidsai Cuml Sklearn Zero Code Acceleration
- Workflow:Predibase Lorax OpenAI Chat Completion
- Workflow:Predibase Lorax Structured JSON Output
- Workflow:Puppeteer Puppeteer Page Screenshot Capture
- Workflow:Apache Airflow Core Release Process
- Workflow:Open compass VLMEvalKit Video Benchmark Evaluation
- Workflow:Cohere ai Cohere python Semantic Search With Rerank
- Workflow:DistrictDataLabs Yellowbrick Feature Analysis and Selection
- Workflow:Spcl Graph of thoughts Custom GoT Use Case Integration
- Workflow:Huggingface Optimum FX Graph Optimization
Principles
- Principle:Guardrails ai Guardrails Structured Guard Execution
- Principle:Huggingface Datatrove Pipeline Failure Diagnosis
- Principle:HKUDS AI Trader Conversation Extraction
- Principle:Run llama Llama index Ingestion Pipeline Construction
- Principle:ArroyoSystems Arroyo Connection Testing
- Principle:Ggml org Llama cpp Speculative Decoding
- Principle:Apache Paimon Ingestion Verification
- Principle:Pytorch Serve Accelerate Device Mapping
- Principle:Huggingface Datasets Streaming Map Transform
- Principle:Huggingface Trl DPO Argument Configuration
Implementations
- Implementation:Kubeflow Kubeflow Roadmap Documentation
- Implementation:Puppeteer Puppeteer Cdp HTTPRequest
- Implementation:Apache Kafka Kafka Run Class Classpath
- Implementation:Apache Beam PipelineMessageReceiver
- Implementation:NVIDIA TransformerEngine TP Group Setup
- Implementation:Lance format Lance Java MergeOp
- Implementation:Langfuse Langfuse Seed Postgres
- Implementation:Microsoft LoRA Legacy Run OpenAI GPT
- Implementation:Infiniflow Ragflow UseFileRequest Hooks
- Implementation:Microsoft Autogen Studio Chat Input
Heuristics
- Heuristic:Bigscience workshop Petals Short Inference Pool Merging
- Heuristic:Huggingface Alignment handbook DPO Beta Selection
- Heuristic:Datajuicer Data juicer Partition Size Tuning
- Heuristic:Langgenius Dify Credential Sanitization In API Responses
- Heuristic:Mlc ai Mlc llm FlashInfer KV Cache Fallback
- Heuristic:Explodinggradients Ragas Deprecation Migration Guide
- Heuristic:Facebookresearch Habitat lab VER Tuning Guidelines
- Heuristic:Liu00222 Open Prompt Injection Defense Strategy Selection
- Heuristic:Iamhankai Forest of Thought Early Stop Majority Vote
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
Environments
- Environment:Astronomer Astronomer cosmos Cosmos Airflow Configuration
- Environment:Helicone Helicone Python ClickHouse Migrations
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:CARLA simulator Carla Python API Runtime
- Environment:Langchain ai Langgraph Docker Deployment Environment
- Environment:Google research Deduplicate text datasets Python TFDS Environment
- Environment:Haosulab ManiSkill Motion Planning Deps
- Environment:EvolvingLMMs Lab Lmms eval API Credentials Environment
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Huggingface Transformers Flash Attention 2 Env