10-01-2026, 12:49 AM
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once prefill/decode split becomes important.
Trying to avoid rebuilding the whole thing twice.
Two paths both seem viable, but they break down differently once prefill/decode split becomes important.
Trying to avoid rebuilding the whole thing twice.
small models can still be useful