server: Add "tokens per second" information in the backend (#10548)
* add cmake rvv support * add timings * remove space * update readme * fix * fix code * remove empty line * add test --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
H
haopeng committed
64ed2091b24b2f9747148fdf49a34ed5938762c3
Parent: 991f8aa
Committed by GitHub <noreply@github.com>
on 12/2/2024, 1:45:54 PM