llama-cpp-server/start-llama-router.ps1

[Console]::InputEncoding = [System.Text.UTF8Encoding]::new($false)
[Console]::OutputEncoding = [System.Text.UTF8Encoding]::new($false)
$OutputEncoding = [Console]::OutputEncoding
$env:PYTHONIOENCODING = 'utf-8'
$env:PYTHONUTF8 = '1'
$ErrorActionPreference = 'Stop'
Set-StrictMode -Version Latest

$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
$ServerExe = 'llama-server.exe'

# === 基础路径 / Base paths ===
$LlamaBin = 'D:\llama'
$ModelsDir = 'E:\LMStudio\.lmstudio\models'
$Preset = Join-Path $ScriptDir 'models-preset.ini'
$Python = 'python'

# === 网络 / Network ===
$LLAMA_Host = '127.0.0.1'
$Port = 18003
$Timeout = ''
$ThreadsHttp = ''

# === Router 行为 / Router behavior ===
$Ttl = 300
$ModelsMax = 1
$RegeneratePreset = $true
$ApiKey = ''
$ApiKeyFile = ''
$CacheRam = ''
$EnableMetrics = $false
$EnableUi = $false
$NoUi = $false
$SslCertFile = ''
$SslKeyFile = ''

$LlamaServer = Join-Path $LlamaBin $ServerExe
if (-not (Test-Path $LlamaServer)) {
    throw "llama-server.exe not found: $LlamaServer"
}

Write-Host '============================================'
Write-Host ' llama.cpp Router Server'
Write-Host ' LM Studio-like router mode with ASR support'
Write-Host '============================================'
Write-Host ''
Write-Host " llama-server: $LlamaServer"
Write-Host " Models dir:   $ModelsDir"
Write-Host " Preset file:  $Preset"
Write-Host " Host:         $LLAMA_Host"
Write-Host " Port:         $Port"
Write-Host " TTL:          ${Ttl}s"
Write-Host " Models max:   $ModelsMax"
Write-Host ''

if ($RegeneratePreset) {
    Write-Host 'Regenerating models preset / 重新生成模型预设...'
    & $Python (Join-Path $ScriptDir 'generate_models_preset.py') `
        --models-dir $ModelsDir `
        --output $Preset `
        --select all `
        --profile smart `
        --alias-style section
    if ($LASTEXITCODE -ne 0) {
        throw 'Failed to generate models-preset.ini'
    }
    Write-Host ''
}

$Args = @(
    '--models-dir', $ModelsDir,
    '--models-preset', $Preset,
    '--models-autoload',
    '--models-max', "$ModelsMax",
    '--sleep-idle-seconds', "$Ttl",
    '--cache-idle-slots',
    '--host', $LLAMA_Host,
    '--port', "$Port"
)

if ($ApiKey) {
    $Args += @('--api-key', $ApiKey)
}

if ($ApiKeyFile) {
    $Args += @('--api-key-file', $ApiKeyFile)
}

if ($Timeout) {
    $Args += @('--timeout', "$Timeout")
}

if ($CacheRam) {
    $Args += @('--cache-ram', "$CacheRam")
}

if ($ThreadsHttp) {
    $Args += @('--threads-http', "$ThreadsHttp")
}

if ($EnableMetrics) {
    $Args += '--metrics'
}

if ($EnableUi) {
    $Args += '--ui'
}

if ($NoUi) {
    $Args += '--no-ui'
}

if ($SslCertFile) {
    $Args += @('--ssl-cert-file', $SslCertFile)
}

if ($SslKeyFile) {
    $Args += @('--ssl-key-file', $SslKeyFile)
}

& $LlamaServer @Args
exit $LASTEXITCODE