UVM to avoid over | Triton Inference Server Feature Requests

UVM to avoid over subscribing GPU memory

Want to be able to load more models into TRTIS GPU memory. Concerned about the inability to anticipate GPU memory consumption/fragmentation. Having UVM would solve this

Guest
Aug 27 2019

Comments (0)

Attach files

Enter a subject

UVM to avoid over subscribing GPU memory

Identify yourself with your email address

Related ideas