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:Openai Whisper Audio Transcription
- Workflow:Risingwavelabs Risingwave Iceberg Lakehouse Ingestion
- Workflow:Iamhankai Forest of Thought FoT Benchmark Evaluation
- Workflow:Neuml Txtai Agent Execution
- Workflow:Getgauge Taiko Interactive Test Recording
- Workflow:Openai CLIP Linear probe evaluation
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:Hpcaitech ColossalAI DPO Alignment
- Workflow:Run llama Llama index ReAct Agent
- Workflow:FlagOpen FlagEmbedding Embedder Inference
Principles
- Principle:Deepseek ai Janus CFG Input Preparation for Flow
- Principle:MaterializeInc Materialize Upgrade Scenario Execution
- Principle:Huggingface Datatrove Language Filtering
- Principle:ThreeSR Awesome Inference Time Scaling Git Automation
- Principle:Ggml org Ggml Optimizer Configuration
- Principle:Isaac sim IsaacGymEnvs Factory Scene Initialization
- Principle:Alibaba MNN Model Format Conversion
- Principle:FMInference FlexLLMGen CUDA Quantization Utilities
- Principle:Haifengl Smile Matrix Arithmetic
- Principle:AUTOMATIC1111 Stable diffusion webui Token Management
Implementations
- Implementation:Scikit learn Scikit learn BenchRandomProjections
- Implementation:ARISE Initiative Robosuite LegBaseModel
- Implementation:Openai Openai node Grader Models
- Implementation:Mlc ai Mlc llm Event Trace Recorder Py
- Implementation:SeleniumHQ Selenium Closure UI MenuButton
- Implementation:Risingwavelabs Risingwave ConnectorService Main
- Implementation:Mage ai Mage ai Target Drain All
- Implementation:Apache Paimon View
- Implementation:ArroyoSystems Arroyo Aws Credential Provider
- Implementation:EvolvingLMMs Lab Lmms eval LLM Judge Protocol
Heuristics
- Heuristic:Langchain ai Langchain Warning Deprecated Langchain Classic
- Heuristic:Huggingface Diffusers VAE Scaling Factors
- Heuristic:AnswerDotAI RAGatouille Searcher Configuration By Collection Size
- Heuristic:Huggingface Optimum Version Conditional Behavior
- Heuristic:Ggml org Llama cpp Batch Size BLAS Minimum
- Heuristic:Teamcapybara Capybara Async Waiting And Retry
- Heuristic:Mlflow Mlflow Nested Run Organization
- Heuristic:Microsoft Playwright Timeout Configuration Tips
- Heuristic:Bentoml BentoML Worker Count Strategy
- Heuristic:Princeton nlp SimPO Left Truncation Strategy
Environments
- Environment:InternLM Lmdeploy Python Dependencies
- Environment:Mage ai Mage ai Python 3 9 Runtime
- Environment:PacktPublishing LLM Engineers Handbook API Credentials
- Environment:ChenghaoMou Text dedup Suffix Array External Tools
- Environment:Huggingface Open r1 CUDA Environment
- Environment:Apache Kafka Docker Build Environment
- Environment:Marker Inc Korea AutoRAG API Keys Configuration
- Environment:Triton inference server Server TRT LLM Deployment
- Environment:Turboderp org Exllamav2 Flash Attention Backend
- Environment:Pola rs Polars Cloud Storage Environment