Join Slack
Powered by
This message was deleted.
# ask-for-help
s
Slackbot
02/23/2023, 8:59 PM
This message was deleted.
c
Chaoyu
02/23/2023, 9:13 PM
Hi Amar, I assume you mean Nvidia TensorRT?
Chaoyu
02/23/2023, 9:15 PM
Yes it is supported in the ongoing BentoML & Triton Integration work, where user can use the TensorRT backend in Triton
Chaoyu
02/23/2023, 9:16 PM
BentoML itself also supports TensorRT, you can use the TensorRT’s python API to load and run a model via custom runner
Chaoyu
02/23/2023, 9:16 PM
https://docs.bentoml.org/en/latest/concepts/runner.html#custom-runner
a
Amar Ramesh Kamat
02/23/2023, 10:00 PM
@Chaoyu
I meant triton inference sever
c
Chaoyu
02/23/2023, 10:20 PM
got it, a beta version is coming out in the next release
a
Amar Ramesh Kamat
02/24/2023, 10:12 AM
Thanks
@Chaoyu
! Any idea when can we expect the next release ?
4
Views
Open in Slack
Previous
Next