triton-inference-server / server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.
https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html
BSD 3-Clause "New" or "Revised" License
8.34k stars 1.49k forks source link

Can implement the inference process of server interrupt after client interrupt request? #7086

Open LIMr1209 opened 7 months ago

rmccorm4 commented 7 months ago

Hi @LIMr1209,

Can you please elaborate on your description to have more details on the request, as well as the use case, requirements, etc.?