Generate macOS/Metal serve commands and surface the Metal GPU

cookbook_routes.py adds a macOS serve path (Ollama, Metal-aware
llama.cpp build using `sysctl hw.ncpu` instead of `nproc`, and a clear
error if vLLM is attempted). The frontend defaults Metal serving to
llama.cpp and offers llama.cpp/Ollama instead of vLLM/SGLang. The
odysseus-cookbook CLI's `gpus` command reports the Metal GPU via
sysctl/vm_stat.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

static/js/cookbook.js

@@ -171,6 +171,13 @@ export function _isWindows(hostOrTask) {
   return _getPlatform(hostOrTask) === 'windows';
 }
 
+/** Check if the detected (local) hardware is Apple Silicon / Metal. Keys off the
+ *  hardware probe's backend rather than a platform string, since a local Mac
+ *  reports no platform but does report backend: "metal". */
+export function _isMetal() {
+  return ['metal', 'mps', 'apple'].includes(String(_hwfitCache?.system?.backend || '').toLowerCase());
+}
+
 /** Detect model-specific vLLM optimizations */
 function _detectModelOptimizations(modelName) {
   const n = (modelName || '').toLowerCase();
@@ -252,6 +259,13 @@ export function _detectBackend(model) {
     return { backend: 'llamacpp', label: 'llama.cpp' };
   }
 
+  // Apple Silicon (Metal) → llama.cpp (GGUF). vLLM/SGLang are CUDA/ROCm-only and
+  // don't run on macOS; AWQ/GPTQ/FP8 (vLLM-only) models are already filtered out
+  // of metal Cookbook results, so llama.cpp is always the right engine here.
+  if (['metal', 'mps', 'apple'].includes(sysBackend)) {
+    return { backend: 'llamacpp', label: 'llama.cpp' };
+  }
+
   // AWQ / GPTQ / FP8 → vLLM
   if (/^AWQ|^GPTQ/.test(q) || q === 'FP8') {
     return { backend: 'vllm', label: 'vLLM' };
@@ -1761,6 +1775,7 @@ const shared = {
   _sshPrefix,
   _getPlatform,
   _isWindows,
+  _isMetal,
   _buildEnvPrefix,
   _buildServeCmd,
   _shellQuote,

static/js/cookbookServe.js

@@ -16,6 +16,7 @@ let _getPort;
 let _sshPrefix;
 let _getPlatform;
 let _isWindows;
+let _isMetal;
 let _buildEnvPrefix;
 let _buildServeCmd;
 let _shellQuote;
@@ -382,6 +383,8 @@ function _rerenderCachedModels() {
       panelHtml += `<div class="hwfit-serve-row">`;
       const _backendChoices = _isWindows()
         ? [['llamacpp','llama.cpp']]
+        : _isMetal()
+        ? [['llamacpp','llama.cpp'],['ollama','Ollama'],['diffusers','Diffusers']]
         : [['vllm','vLLM'],['sglang','SGLang'],['llamacpp','llama.cpp'],['diffusers','Diffusers']];
       const backendOpts = _backendChoices.map(([v,l]) => `<option value="${v}"${defaultBackend===v?' selected':''}>${l}</option>`).join('');
       panelHtml += `<label>${_l('Backend','Inference engine: vLLM, SGLang, llama.cpp, or Diffusers')}<select class="hwfit-sf" data-field="backend">${backendOpts}</select></label>`;
@@ -1592,6 +1595,7 @@ export function initServe(shared) {
   _sshPrefix = shared._sshPrefix;
   _getPlatform = shared._getPlatform;
   _isWindows = shared._isWindows;
+  _isMetal = shared._isMetal;
   _buildEnvPrefix = shared._buildEnvPrefix;
   _buildServeCmd = shared._buildServeCmd;
   _shellQuote = shared._shellQuote;