server : ensure batches are either all embed or all completion (#8420)
* make sure batches are all embed or all non-embed * non-embedding batch for sampled tokens; fix unused params warning
D
Douglas Hanley committed
c3ebcfa148e867a68e78fd5c4f0c23e8f84c788b
Parent: 8a4441e
Committed by GitHub <noreply@github.com>
on 7/12/2024, 8:14:12 AM