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/deeplab_v3_resnet50_coreml_fp16.pte

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c824e4340751b5d249cec768058f1ac9347bdb9fa46c33c4f59224be6584b6c9
-size 79603960
+oid sha256:af850e6b778a9003cd32545c67a51ce823bc5d8227eb53534f2580a91fc1946f
+size 79613357