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_mobilenet_v3_large_coreml_fp16.pte

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39176a368f1f896c76ef9a0c100141e847d80841ff7d36600747cdd227ef75a7
-size 22537867
+oid sha256:bb7b0a9c15e830b48f52d517743d7c98b403ab21ce701347f92e176d6a54c043
+size 22547278