[GH-ISSUE #4493] How can we make model calls faster #28571

Closed
opened 2026-04-22 06:51:35 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @userandpass on GitHub (May 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4493

What is the issue?

I used docker to load multiple ollama images and distribute them using nginx, which was much slower than calling the deployed model directly

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

0.1.34

Originally created by @userandpass on GitHub (May 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4493 ### What is the issue? I used docker to load multiple ollama images and distribute them using nginx, which was much slower than calling the deployed model directly ### OS Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.1.34
GiteaMirror added the questionneeds more info labels 2026-04-22 06:51:41 -05:00
Author
Owner

@userandpass commented on GitHub (May 17, 2024):

After I added the "keep_alive": "24h" parameter, after a while I executed the nvidia-smi command, there was no ollama on the card, so I needed to call the interface to display it

<!-- gh-comment-id:2117143292 --> @userandpass commented on GitHub (May 17, 2024): After I added the "keep_alive": "24h" parameter, after a while I executed the nvidia-smi command, there was no ollama on the card, so I needed to call the interface to display it
Author
Owner

@dhiltgen commented on GitHub (Oct 16, 2024):

Looks like this issue slipped through the cracks.

I don't quite understand what problem you're having. It sounds like you're running multiple ollama containers, and load balancing them with an nginx in front. When you say "much slower" are you talking about tokens per second, latency, throughput, something else? I think you're indicating that Ollama itself is working properly, but you're having trouble setting up a load balancer in front of it without introducing lag?

<!-- gh-comment-id:2417328856 --> @dhiltgen commented on GitHub (Oct 16, 2024): Looks like this issue slipped through the cracks. I don't quite understand what problem you're having. It sounds like you're running multiple ollama containers, and load balancing them with an nginx in front. When you say "much slower" are you talking about tokens per second, latency, throughput, something else? I think you're indicating that Ollama itself is working properly, but you're having trouble setting up a load balancer in front of it without introducing lag?
Author
Owner

@pdevine commented on GitHub (Jan 12, 2025):

Let's close the issue. We can reopen if it's still a problem.

<!-- gh-comment-id:2585500194 --> @pdevine commented on GitHub (Jan 12, 2025): Let's close the issue. We can reopen if it's still a problem.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#28571