llama: add --dry-run option (#1462)

Co-authored-by: firecoperana <firecoperana>

include/llama.h

@@ -401,6 +401,7 @@ extern "C" {
         bool merge_qkv;     // if true, merge separate Q, K, V tensors into a single, contiguous tensor
         bool merge_up_gate_exps;  // if true, merge ffn_up_exps and ffn_gate_exps tensors into a single, contiguous tensor
         bool mtp;           // if true, load MTP layers if present
+        bool dry_run;       // skip loading tensors
     };
 
     // NOTE: changing the default values of parameters marked as [EXPERIMENTAL] may cause crashes or incorrect results in certain configurations