Layout when running in vllm container
#26
by
swtb
- opened
Hi,
I have this model running in a VLLM docker container. Is it possible to get the layout details when inferencing in this way? If so, How?
If not, what is the best way to serve this with layout included?
Nevermind.
For those that follow. The bbox info is written in the tags.
swtb
changed discussion status to
closed