search

triton-inference-server / pytriton

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
https://triton-inference-server.github.io/pytriton/
Apache License 2.0
687 stars 45 forks source link

[Question] will the server fork several subprocess when infer_func is a list? #73

Closed leafjungle closed 2 months ago

leafjungle commented 2 months ago

How does the server process the requests in parallel?

subprocess or threads?

leafjungle commented 2 months ago

after test it is process, no threads