Add bounded GPU-priority automatic model testing and profile export

inference.py

@@ -124,7 +124,10 @@ class LlamaWorker:
             self.stop()
             with self.lock:self.state='failed';self.phase='Modellstart fehlgeschlagen';self.error=str(exc) if isinstance(exc,ValueError) else 'llama.cpp konnte nicht gestartet werden.'
             raise InferenceError(self.error) from None
-    def _start(self,profile,generation,cancel=lambda:False):
+    def plan(self,profile,cancel=lambda:False):
+        self._start(profile,self.generation,cancel,plan_only=True)
+        return self.memory_plan
+    def _start(self,profile,generation,cancel=lambda:False,plan_only=False):
         directory=self.build();params=profile['parameters'];entry=self.catalog.entry(profile['model_id'])
         model=(self.catalog.root/entry['id']/('model'+Path(entry['file']).suffix)).resolve()
         mtp=params.get('mtp',False)
@@ -197,6 +200,7 @@ class LlamaWorker:
             fits,memory=estimate(layers,extra)
             if not fits:raise InferenceError('Speicherprognose überschreitet die GPU-/RAM-Reserve.')
         if cancel():raise InferenceError('Modellstart abgebrochen.')
+        if plan_only:return
         with self.lock:self.phase='Modell wird geladen'
         launch=common+extra+['--gpu-layers',str(layers),'--fit','off','--kv-unified','--threads',str(params['threads']),'--load-mode','none','--host','127.0.0.1','--alias',profile['name'],'--no-webui','--log-disable']
         if mtp:launch+=['--spec-type','draft-mtp','--spec-draft-n-max',str(params.get('mtp_tokens',2)),'--spec-draft-p-min',str(params.get('mtp_min_p',.05)),'--spec-draft-type-k','f16','--spec-draft-type-v','f16']