[GH-ISSUE #7928] ollama api(port:11434)Regarding parallel processing and CPU single core usage #82757

Closed
opened 2026-05-09 15:44:36 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @dmmhk on GitHub (Dec 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7928

Regarding parallel processing and CPU single core usage
API :http://localhost:11434/api/generate
The waiting time for API requests simultaneously is too long,CPU processing does not use multi-core;

Are there any optimization methods available?

OS
Windows 11
GPU
Nvidia 3080 16G
CPU
AMD R9 5900HX
Ollama version
0.4.5

Originally created by @dmmhk on GitHub (Dec 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7928 **Regarding parallel processing and CPU single core usage** API :http://localhost:11434/api/generate The waiting time for API requests simultaneously is too long,CPU processing does not use multi-core; Are there any optimization methods available? **OS** Windows 11 **GPU** Nvidia 3080 16G **CPU** AMD R9 5900HX **Ollama version** 0.4.5
GiteaMirror added the feature requestneeds more info labels 2026-05-09 15:44:36 -05:00
Author
Owner

@rick-github commented on GitHub (Dec 4, 2024):

Server logs may aid in debugging. Have you set OLLAMA_NUM_PARALLEL?

<!-- gh-comment-id:2517136445 --> @rick-github commented on GitHub (Dec 4, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging. Have you set `OLLAMA_NUM_PARALLEL`?
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#82757