CPU Tasks
LoadModel       2.20693 seconds
RunComplete     3.16174 seconds
Run     3.07912 seconds
Callbacks       387.3 microseconds, 4 calls, 96.825 microseconds average
Spectrogram     16.201 milliseconds, 3 calls, 5.40033 milliseconds average
Sample  3.3725 milliseconds, 28 calls, 120.446 microseconds average
Encode  2.07037 seconds
Decode  1.00834 seconds
DecodeStep      1.00495 seconds, 28 calls, 35.8911 milliseconds average
    GPU Tasks
LoadModel       1.81217 seconds
Run     2.94117 seconds
Encode  1.95373 seconds
EncodeLayer     1.56747 seconds, 24 calls, 65.3115 milliseconds average
Decode  987.441 milliseconds
DecodeStep      987.44 milliseconds, 28 calls, 35.2657 milliseconds average
DecodeLayer     915.401 milliseconds, 672 calls, 1.3622 milliseconds average
    Compute Shaders
mulMatTiled     1.68817 seconds, 529 calls, 3.19125 milliseconds average
mulMatByRowTiled        562.722 milliseconds, 7803 calls, 72.1161 microseconds average
convolutionMain2Fixed   99.873 milliseconds
softMaxFixed    84.045 milliseconds, 696 calls, 120.754 microseconds average
copyTranspose   80.3619 milliseconds, 1392 calls, 57.7313 microseconds average
fmaRepeat1      71.9629 milliseconds, 2093 calls, 34.3827 microseconds average
convolutionMain 60.588 milliseconds
addRepeatScale  53.2349 milliseconds, 1344 calls, 39.6093 microseconds average
normFixed       34.7651 milliseconds, 2093 calls, 16.6102 microseconds average
addRepeatEx     31.9206 milliseconds, 2064 calls, 15.4654 microseconds average
copyConvert     30.7856 milliseconds, 1440 calls, 21.3789 microseconds average
addRepeatGelu   25.5167 milliseconds, 698 calls, 36.5569 microseconds average
softMaxLong     25.3214 milliseconds, 28 calls, 904.336 microseconds average
scaleInPlace    24.1527 milliseconds, 696 calls, 34.7022 microseconds average
softMax 21.0692 milliseconds, 672 calls, 31.353 microseconds average
addRepeat       19.8584 milliseconds, 744 calls, 26.6914 microseconds average
diagMaskInf     12.5615 milliseconds, 672 calls, 18.6927 microseconds average
convolutionPrep1        6.113 milliseconds, 2 calls, 3.0565 milliseconds average
convolutionPrep2        1.2294 milliseconds, 2 calls, 614.7 microseconds average
add     532.9 microseconds
addRows 178.9 microseconds, 28 calls, 6.38929 microseconds average
    Memory Usage
Model   877.966 KB RAM, 1.42785 GB VRAM
Context 1.9831 MB RAM, 723.782 MB VRAM
Total   2.84049 MB RAM, 2.13467 GB VRAM