Add LM Backend selector (PT vs VLLM) to reduce VRAM usage

PT backend uses ~1.6 GB VRAM vs ~9.2 GB for VLLM, making it accessible
on lower-end GPUs. Adds dropdown in Advanced Settings defaulting to PT.

types.ts

@@ -83,6 +83,7 @@ export interface GenerationParams {
   lmTopK: number;
   lmTopP: number;
   lmNegativePrompt: string;
+  lmBackend?: 'pt' | 'vllm';
 
   // Expert Parameters
   referenceAudioUrl?: string;