github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9432] 无法调用全部CPU #68206

New Issue
Closed
opened 2026-05-04 12:50:39 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-04 12:50:39 -05:00
Owner
Copy Link

Originally created by @xhdndmm on GitHub (Feb 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9432

Originally assigned to: @jmorganca on GitHub.

What is the issue?

无法调用全部的CPU 只能使用50% 像这样
Image

Relevant log output

OS

Linux

GPU

N/A

CPU

EPYC 7D12

Ollama version

0.5.11

Originally created by @xhdndmm on GitHub (Feb 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9432 Originally assigned to: @jmorganca on GitHub. ### What is the issue? 无法调用全部的CPU 只能使用50% 像这样 ![Image](https://github.com/user-attachments/assets/e9d2e0f1-71e6-4771-bb40-64db1755eaca) ### Relevant log output ```shell ``` ### OS Linux ### GPU N/A ### CPU EPYC 7D12 ### Ollama version 0.5.11
GiteaMirror added the bug label 2026-05-04 12:50:39 -05:00
GiteaMirror commented 2026-05-04 12:50:43 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 28, 2025):

@xhdndmm possible to try 0.5.12? Improvements were made to CPU performance

<!-- gh-comment-id:2691716492 --> @jmorganca commented on GitHub (Feb 28, 2025): @xhdndmm possible to try 0.5.12? Improvements were made to CPU performance
GiteaMirror commented 2026-05-04 12:50:44 -05:00
Author
Owner
Copy Link

@xhdndmm commented on GitHub (Feb 28, 2025):

@xhdndmm可以尝试 0.5.12 吗？CPU 性能有所改进

我升级了0.5.12 但是还是只能调用50%的CPU

<!-- gh-comment-id:2691733275 --> @xhdndmm commented on GitHub (Feb 28, 2025): > [@xhdndmm](https://github.com/xhdndmm)可以尝试 0.5.12 吗？CPU 性能有所改进 我升级了0.5.12 但是还是只能调用50%的CPU
GiteaMirror commented 2026-05-04 12:50:46 -05:00
Author
Owner
Copy Link

@luckycv commented on GitHub (Mar 1, 2025):

计算密集型，使用物理核心数会相对更高效。

<!-- gh-comment-id:2692037485 --> @luckycv commented on GitHub (Mar 1, 2025): 计算密集型，使用物理核心数会相对更高效。
GiteaMirror commented 2026-05-04 12:50:47 -05:00
Author
Owner
Copy Link

@luckycv commented on GitHub (Mar 1, 2025):

推理的时候，使用cpu的逻辑核心数并不会高于物理核心数表现，ollama 本身专门对这个优化。你可以本地编译代码更改线程数测试 token 生成速度

<!-- gh-comment-id:2692040612 --> @luckycv commented on GitHub (Mar 1, 2025): 推理的时候，使用cpu的逻辑核心数并不会高于物理核心数表现，ollama 本身专门对这个优化。你可以本地编译代码更改线程数测试 token 生成速度
GiteaMirror commented 2026-05-04 12:50:49 -05:00
Author
Owner
Copy Link

@xhdndmm commented on GitHub (Mar 1, 2025):

推理的时候，使用cpu的逻辑核心数并不会高于物理核心数表现，ollama 本身专门对这个优化。你可以本地编译代码更改线程数测试 token 生成速度

知道了 谢谢

<!-- gh-comment-id:2692075221 --> @xhdndmm commented on GitHub (Mar 1, 2025): > 推理的时候，使用cpu的逻辑核心数并不会高于物理核心数表现，ollama 本身专门对这个优化。你可以本地编译代码更改线程数测试 token 生成速度 知道了 谢谢
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#68206
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?