paired P=10180 nt=1 mrope=0 attn=1 (memcmp PASS), ref / candidate GPU us
prep 7.260 / 7.305 (ratio 0.9993)
score 5.266 / 5.281 (ratio 1.0030)
topk 8.297 / 7.878 (ratio 0.9482)
attn 46.211 / 46.466 (ratio 1.0017)
merge 5.760 / 4.130 (ratio 0.7170)
paired P=10180 nt=2 mrope=0 attn=1 (memcmp PASS), ref / candidate GPU us
prep 8.953 / 8.914 (ratio 1.0026)
score 39.716 / 38.818 (ratio 0.9977)
topk 8.440 / 8.391 (ratio 0.9883)
attn 83.565 / 83.771 (ratio 1.0018)
merge 6.781 / 5.469 (ratio 0.8099)
paired P=10180 nt=3 mrope=0 attn=1 (memcmp PASS), ref / candidate GPU us
prep 10.867 / 10.898 (ratio 1.0029)
score 57.008 / 57.117 (ratio 1.0002)
topk 39.073 / 39.734 (ratio 1.0099)
attn 125.500 / 125.396 (ratio 0.9989)
merge 16.398 / 17.466 (ratio 1.0660)
paired P=10180 nt=4 mrope=0 attn=1 (memcmp PASS), ref / candidate GPU us
prep 12.206 / 12.245 (ratio 1.0071)
score 16.836 / 16.833 (ratio 1.0014)
topk 8.242 / 8.302 (ratio 1.0025)
attn 161.979 / 161.953 (ratio 1.0000)
merge 23.547 / 22.190 (ratio 0.9424)
paired P=10180 nt=8 mrope=0 attn=1 (memcmp PASS), ref / candidate GPU us
prep 7.641 / 7.750 (ratio 1.0087)
score 32.688 / 32.781 (ratio 1.0019)
topk 8.260 / 8.143 (ratio 0.9987)
attn 325.305 / 325.188 (ratio 0.9995)
merge 46.406 / 44.102 (ratio 0.9527)
paired P=10180 nt=1984 mrope=0 attn=1 (memcmp PASS), ref / candidate GPU us
prep 976.844 / 988.021 (ratio 1.0023)
paired P=10180 nt=2048 mrope=0 attn=1 (memcmp PASS), ref / candidate GPU us
prep 1005.812 / 1016.844 (ratio 1.0068)