feat: deteccion de GPU NVIDIA y aceleracion automatica

- Detecta nvidia-smi (driver Windows 535+ hace passthrough a WSL2)
- Con GPU: ollama arranca con --gpus all (docker run) / override
  compose docker-compose.gpu.yml (gpus: all) -> 30-50 tok/s
- Sin GPU: como hasta ahora (CPU ~10-20 tok/s) + aviso honesto

wordpress/deploy.ps1

@@ -119,6 +119,19 @@ if (-not (Test-Path $EnvFile)) {
     Info "Contrasenas generadas en $EnvFile"
 }
 
+# --- GPU NVIDIA? (si hay, Ollama la usa y va 5-10x mas rapido) ---------------
+$HasGpu = $false
+if (Get-Command nvidia-smi -ErrorAction SilentlyContinue) {
+    $GpuInfo = & nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null
+    if ($LASTEXITCODE -eq 0 -and $GpuInfo) {
+        $HasGpu = $true
+        $GpuName = ($GpuInfo -split ',')[0].Trim()
+        Info "GPU NVIDIA detectada: $GpuName (aceleracion activada)"
+    }
+}
+if (-not $HasGpu) {
+    Warn 'Sin GPU NVIDIA: modo CPU (~10-20 tokens/s). Con una GPU NVIDIA va 5-10x mas rapido.'
+}
 # --- Auto-detect ports ----------------------------------------------------
 # --- Tumbar deploy previo (antes de detectar puertos) ----------------------
 cmd /c docker compose -f $ComposeFile down '>' NUL '2>&1'
@@ -161,7 +174,13 @@ cmd /c docker compose -f $ComposeFile down '>' NUL '2>&1'
 $env:OLLAMA_PORT = "$OllamaPort"
 $env:WP_PORT     = "$WpPort"
 $env:WEBUI_PORT  = "$WebUiPort"
-docker compose -f $ComposeFile up -d
+$ComposeArgs = @('-f', $ComposeFile)
+if ($HasGpu) {
+    $OverrideFile = Join-Path $ScriptDir 'docker-compose.gpu.yml'
+    Set-Content -Path $OverrideFile -Value "services:`r`n  ollama:`r`n    gpus: all`r`n"
+    $ComposeArgs += @('-f', $OverrideFile)
+}
+docker compose @ComposeArgs up -d
 if ($LASTEXITCODE -ne 0) { Err "docker compose up fallo (exit $LASTEXITCODE)."; exit 1 }
 
 # --- Pull model -------------------------------------------------------------