speculative : PoC for speeding-up inference via speculative sampling (#2926)
* speculative : initial example * speculative : print encoding speed * speculative : add --draft CLI arg
G
Georgi Gerganov committed
47068e517004d90f13c16352bb3b4cafd53a00cd
Parent: 8f429fa
Committed by GitHub <noreply@github.com>
on 9/3/2023, 12:12:08 PM