You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
After specifying a minimum OS version of macOS13 and iOS16, there is still a large matrix of possible model-device configurations for deployment:
Devices have varying capabilities across:
Available RAM: Ranging from 4GB on iPhone 12 mini to 192GB on M2 Ultra Mac Studio
Chip generation: A12 (iPhone XS) to A17 Pro (iPhone 15 Pro), M1-M3 for Mac and iPads etc. , S9 SiP for Apple Watch
Apple Silicon vs legacy Intel Macs (still supported by macOS 14)
Model versions that have varying requirements:
Original variants: tiny, base, small, large distil-large
Argmax variants: compressed, turbo and compressed+turbo
Not all model versions will successfully run on all Apple devices. Some combinations may be enabled in the future by Argmax work. Some combinations may be disabled due to OS regressions. Hence, we would like to automatically test all combinations before each release using the testing infrastructure being laid out in #99 by @Abhinay1997 and throw unsupportedModelDeviceCombination for combinations that fail to pass all the tests during WhisperKit pipeline init time.
Taking it a step further, the WhisperKit pipeline object should be able to take an optional "peakMemoryAllowed" argument at init time and compare that against the peak memory recorded during test on the particular model-device combination and throw unsupportedModelDeviceCombination.
For the time being, we will disable all Intel Macs. Please reach out if you need Intel Macs support for your product.
The text was updated successfully, but these errors were encountered:
That sounds great! Additionally it would be great if there was maybe a function that took an enum parameter indicating what the priority was (e.g. speed, quality, low-memory), and WhisperKit would return a recommended model / a short short list of recommended models that would be the best fit for the current system.
After specifying a minimum OS version of macOS13 and iOS16, there is still a large matrix of possible model-device configurations for deployment:
Devices have varying capabilities across:
Model versions that have varying requirements:
Not all model versions will successfully run on all Apple devices. Some combinations may be enabled in the future by Argmax work. Some combinations may be disabled due to OS regressions. Hence, we would like to automatically test all combinations before each release using the testing infrastructure being laid out in #99 by @Abhinay1997 and throw
unsupportedModelDeviceCombination
for combinations that fail to pass all the tests duringWhisperKit
pipeline init time.Taking it a step further, the
WhisperKit
pipeline object should be able to take an optional "peakMemoryAllowed" argument at init time and compare that against the peak memory recorded during test on the particular model-device combination and throwunsupportedModelDeviceCombination
.For the time being, we will disable all Intel Macs. Please reach out if you need Intel Macs support for your product.
The text was updated successfully, but these errors were encountered: