fix: limite de RAM 6G para ollama

Sin cap, ollama crece sin freno (visto en docker stats: 3.94 GB y
subiendo). Cap 6G suficiente para llama3.2:3b Q4 + ctx 16k:
- compose (openwebui, wordpress): deploy.resources.limits.memory 6G
- docker run (hermes, openclaw): --memory 6g

hermes/deploy.ps1

@@ -83,19 +83,6 @@ Ok "RAM: $TotalRamGb GB"
 # --- Tumbar deploy previo (antes de detectar puertos) -----------------------
 cmd /c docker rm -f d0a1-hermes-ollama '>' NUL '2>&1'
 
-# --- 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 Ollama port ------------------------------------------------
 $OllamaPort = Find-FreePort 11434
 
@@ -114,9 +101,7 @@ Write-Host ''
 Warn '[1/3] Arrancando Ollama (IA local)...'
 $running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-hermes-ollama'
 if (-not $running) {
-    $GpuArgs = @()
+    docker run -d --name d0a1-hermes-ollama --memory 6g `
-    if ($HasGpu) { $GpuArgs = @('--gpus', 'all') }
-    docker run -d --name d0a1-hermes-ollama --memory 6g @GpuArgs `
         -p "${OllamaPort}:11434" `
         -v d0a1_hermes_ollama:/root/.ollama `
         -e OLLAMA_HOST=0.0.0.0 `

openclaw/deploy.ps1

@@ -83,19 +83,6 @@ Ok "RAM: $TotalRamGb GB"
 # --- Tumbar deploy previo (antes de detectar puertos) -----------------------
 cmd /c docker rm -f d0a1-openclaw-ollama '>' NUL '2>&1'
 
-# --- 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 Ollama port ------------------------------------------------
 $OllamaPort = Find-FreePort 11434
 
@@ -114,9 +101,7 @@ Write-Host ''
 Warn '[1/3] Arrancando Ollama (IA local)...'
 $running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-openclaw-ollama'
 if (-not $running) {
-    $GpuArgs = @()
+    docker run -d --name d0a1-openclaw-ollama --memory 6g `
-    if ($HasGpu) { $GpuArgs = @('--gpus', 'all') }
-    docker run -d --name d0a1-openclaw-ollama --memory 6g @GpuArgs `
         -p "${OllamaPort}:11434" `
         -v d0a1_openclaw_ollama:/root/.ollama `
         -e OLLAMA_HOST=0.0.0.0 `

openwebui/deploy.ps1

@@ -91,19 +91,6 @@ Ok "RAM: $TotalRamGb GB"
 # los puertos para que Find-FreePort vea el estado REAL tras el down.
 cmd /c docker compose -f $ComposeFile down '>' NUL '2>&1'
 
-# --- 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 ----------------------------------------------------
 $OllamaPort = Find-FreePort 11434
 $WebUiPort  = Find-FreePort 3000
@@ -137,13 +124,7 @@ Write-Host ''
 Warn 'Descargando contenedores (2-3 min la primera vez)...'
 $env:OLLAMA_PORT = "$OllamaPort"
 $env:WEBUI_PORT  = "$WebUiPort"
-$ComposeArgs = @('-f', $ComposeFile)
+docker compose -f $ComposeFile up -d
-if ($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 -------------------------------------------------------------

wordpress/deploy.ps1

@@ -119,19 +119,6 @@ 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'
@@ -174,13 +161,7 @@ cmd /c docker compose -f $ComposeFile down '>' NUL '2>&1'
 $env:OLLAMA_PORT = "$OllamaPort"
 $env:WP_PORT     = "$WpPort"
 $env:WEBUI_PORT  = "$WebUiPort"
-$ComposeArgs = @('-f', $ComposeFile)
+docker compose -f $ComposeFile up -d
-if ($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 -------------------------------------------------------------