Skip to content

Conversation

@JEMeyer
Copy link

@JEMeyer JEMeyer commented May 1, 2024

I wanted to be able to consume my own instances without worrying about having to queue/proxy calls via another web server.

Added in threading to get the lock object - api endpoints then are wrapped with a with lock: in order to ensure only 1 request is actually using the gpu at a time.

WeberJulian and others added 3 commits April 23, 2024 01:04
disable threading to allow production use

accidenatlly setup like it was flask not fastapi - use locks instead
@CLAassistant
Copy link

CLAassistant commented May 1, 2024

CLA assistant check
All committers have signed the CLA.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants