haopeng 64ed2091b2 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>

2024-12-02 14:45:54 +01:00

139 KiB

Raw Blame History

View Raw