12345device Apple M5; IQ2_S/Q2_0, T 1, 64 experts, tile TM 16 TN 32 TK 32 SG 4right-input layout: runs of 4 kplan: 10 tiles of 16, 160 padded rows for 10 entriesparity: plan ok; y vs fp16-operand reference rel L2 1.62e-05, vs exact float reference 4.61e-04 PASS