10-09-2026, 03:21 PM
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once batch size becomes important.
Interested in tradeoffs more than fan loyalty.
This is mostly for local work rather than public serving.
Two paths both seem viable, but they break down differently once batch size becomes important.
Interested in tradeoffs more than fan loyalty.
This is mostly for local work rather than public serving.
Mostly CUDA, sometimes wrong, usually measured