Core ML: emit a (1,520,520) int32 index map instead of (1,21,520,520) logits

The argmax now runs inside the graph, built from reduce_max and elementwise ops so it stays on the ANE. 1.05x to 1.63x faster and 7 to 48 percent lower peak memory on an iPhone 16. XNNPACK variants are unchanged.

coreml/fcn_resnet50_coreml_fp16.pte

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca7a50a761b5258442148936c6eb98d8fd5b986e1d73c6273be46400e8a621d
-size 66200877
+oid sha256:3cc37b3f1f49f3a23f9c9172fa09698297bd55a1b8cfc406d899563d0ce89f58
+size 66210276