%% GPU Allocation Diagram
%% Shows how AI workloads are distributed across GPU nodes

flowchart TB
    subgraph khelben["🖥️ khelben (AMD Strix Halo 64GB)"]
        direction TB
        vllm["🧠 vLLM<br/>LLM Inference<br/>100% GPU"]
    end

    subgraph elminster["🖥️ elminster (NVIDIA RTX 2070 8GB)"]
        direction TB
        whisper["🎤 Whisper<br/>STT<br/>~50% GPU"]
        xtts["🔊 XTTS<br/>TTS<br/>~50% GPU"]
    end

    subgraph drizzt["🖥️ drizzt (AMD Radeon 680M 12GB)"]
        direction TB
        embeddings["📊 BGE Embeddings<br/>Vector Encoding<br/>~80% GPU"]
    end

    subgraph danilo["🖥️ danilo (Intel Arc)"]
        direction TB
        reranker["📋 BGE Reranker<br/>Document Ranking<br/>~80% GPU"]
    end

    subgraph workloads["Workload Routing"]
        chat["💬 Chat Request"]
        voice["🎤 Voice Request"]
    end

    chat --> embeddings
    chat --> reranker
    chat --> vllm

    voice --> whisper
    voice --> embeddings
    voice --> reranker
    voice --> vllm
    voice --> xtts

    classDef nvidia fill:#76B900,color:white
    classDef amd fill:#ED1C24,color:white
    classDef intel fill:#0071C5,color:white
    
    class whisper,xtts nvidia
    class vllm,embeddings amd
    class reranker intel