@<1523701205467926528:profile|AgitatedDove14> Actually our meant is something like the following example from the triton client examples:

None

Does clearml has any example for using shared memory? or it's out of context for clearml?

Hi @<1547028116780617728:profile|TimelyRabbit96>
Notice that if running with docker compose you can pass an argument to the clearml triton container an use shared mem. You can do the same with the helm chart

Sorry @<1657918706052763648:profile|SillyRobin38> I missed this reply

Is ClearML-Serving using either System or CUCA shared memory? O

This needs to be set on the docker-compose:
and I think this line actually includes ipc: host which means there is no need to set the shm_size, but you can play around with it and let me know if you see a difference
None

@<1523701205467926528:profile|AgitatedDove14> Thanks

I see, okay so using

shm_size: '2gb'

we still need to modify the infrence logic to register and input and output on shmem, no?

@<1657918706052763648:profile|SillyRobin38> ^