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/lraspp_mobilenet_v3_large_coreml_fp16.pte

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25e8fc560662926890cc882b54e5129bb8c8512501ff98ac9a22edd3b646702
-size 6908281
+oid sha256:365b2961edb1771bdd185d301bac1987f9c828fe3f804a72d1d66f867173cf43
+size 6917692