[GH-ISSUE #2845] Multiple requests at once #48244

Closed
opened 2026-04-28 07:19:09 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @trymeouteh on GitHub (Feb 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2845

Would take more computing power on the users machine, but to allow Ollama to be able to make multiple requests at once.

Lets say you have two terminal windows running and you ask the AI in Window 1 to do X and ask the AI in Windows 2 which will either be using the same model or a different model and ask it to do Y and it will do X and Y at the same time, and not wait to do Y once X is done.

Or even if you have one application that integrated Ollama and another application that integrated Ollama, to be able to do X in application 1 and Y in application 2 at the same time.

Originally created by @trymeouteh on GitHub (Feb 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2845 Would take more computing power on the users machine, but to allow Ollama to be able to make multiple requests at once. Lets say you have two terminal windows running and you ask the AI in Window 1 to do X and ask the AI in Windows 2 which will either be using the same model or a different model and ask it to do Y and it will do X and Y at the same time, and not wait to do Y once X is done. Or even if you have one application that integrated Ollama and another application that integrated Ollama, to be able to do X in application 1 and Y in application 2 at the same time.
Author
Owner

@pdevine commented on GitHub (Mar 1, 2024):

Closing as dupe of #358

<!-- gh-comment-id:1972253212 --> @pdevine commented on GitHub (Mar 1, 2024): Closing as dupe of #358
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#48244