Viewing profile — aukejw

I'm also trusting `get_peak_memory` + some small buffer for now. Still, it reports accurate peak memory usage for tensors living on GPU, but seems to miss some of the non-Metal ove…

How do you determine peak memory usage? Just look at activity monitor? I've yet to find a good overview of how much memory each model needs for different context lengths (other tha…

There are plenty of smaller (quantized) models that fit well on your machine! On a M4 with 24GB it’s already possible to comfortably run 8B quantized models. Im benchmarking runtim…

[dead]