llama : do a warm-up eval at start for better timings (#1824)
G
Georgi Gerganov committed
2347e45e7bdb09c9a7d74b2c0bc86c2b65f0c343
Parent: 74d4cfa
Committed by GitHub <noreply@github.com>
on 6/13/2023, 5:20:07 PM