[GH-ISSUE #5249] windows环境,使用api接口调用,,并发请求是多少啊?可以配置吗? #3284

Closed
opened 2026-04-12 13:50:57 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @liuHongyang0207 on GitHub (Jun 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5249

windows环境,使用api接口调用,,并发请求是多少啊?可以配置吗?

为什么有一个请求在传输中,另外一个请求就要排队,,怎么增加并发量啊?

Originally created by @liuHongyang0207 on GitHub (Jun 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5249 windows环境,使用api接口调用,,并发请求是多少啊?可以配置吗? 为什么有一个请求在传输中,另外一个请求就要排队,,怎么增加并发量啊?
GiteaMirror added the feature request label 2026-04-12 13:50:57 -05:00
Author
Owner

@wj2929 commented on GitHub (Jun 24, 2024):

Check the OLLAMA_NUM_PARALLEL setting
Reference link: OLLAMA_NUM_PARALLEL"

<!-- gh-comment-id:2186682676 --> @wj2929 commented on GitHub (Jun 24, 2024): Check the OLLAMA_NUM_PARALLEL setting Reference link: [OLLAMA_NUM_PARALLEL"](https://blog.csdn.net/engchina/article/details/138743634)
Author
Owner

@dhiltgen commented on GitHub (Jun 25, 2024):

The experimental concurrency feature was described briefly in the release notes for 0.1.33. In a future version we will enable this by default.

<!-- gh-comment-id:2189403219 --> @dhiltgen commented on GitHub (Jun 25, 2024): The experimental concurrency feature was described briefly in the [release notes for 0.1.33](https://github.com/ollama/ollama/releases/tag/v0.1.33). In a future version we will enable this by default.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#3284