Currently with two users, the system will only complete requests sequentially. This is the case even when users are using different LiteLLM model providers, and particularly evident when 1 of the 2 users is generating pictures.
Would like the ability for the system to handle parallel API requests to different and\or the same provider.
Have considered deploying Open-WebUI locally for both users or load balancing Open-WebUI itself, but seems extreme for 2 users.
From the comments I hear people with multiple users, wondering if I did something really dumb in the setup.
PS: Latest Image "docker.io/open-webui/open-webui:latest", but this issue has always existed for me, so perhaps user error.
Originally created by @spammenotinoz on GitHub (Aug 5, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/4363
Currently with two users, the system will only complete requests sequentially. This is the case even when users are using different LiteLLM model providers, and particularly evident when 1 of the 2 users is generating pictures.
Would like the ability for the system to handle parallel API requests to different and\or the same provider.
Have considered deploying Open-WebUI locally for both users or load balancing Open-WebUI itself, but seems extreme for 2 users.
From the comments I hear people with multiple users, wondering if I did something really dumb in the setup.
PS: Latest Image "docker.io/open-webui/open-webui:latest", but this issue has always existed for me, so perhaps user error.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @spammenotinoz on GitHub (Aug 5, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/4363
Currently with two users, the system will only complete requests sequentially. This is the case even when users are using different LiteLLM model providers, and particularly evident when 1 of the 2 users is generating pictures.
Would like the ability for the system to handle parallel API requests to different and\or the same provider.
Have considered deploying Open-WebUI locally for both users or load balancing Open-WebUI itself, but seems extreme for 2 users.
From the comments I hear people with multiple users, wondering if I did something really dumb in the setup.
PS: Latest Image "docker.io/open-webui/open-webui:latest", but this issue has always existed for me, so perhaps user error.