github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-11 20:23:55 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

[PR #12396] Fix the inappropriate thread count for Ollama in the Docker scenario #12547

New Issue
Open
opened 2025-11-12 16:38:29 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-12 16:38:29 -06:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12396
Author: @dingdongxiangvolc
Created: 9/24/2025
Status: 🔄 Open

Base: main ← Head: main

📝 Commits (1)

  • d9a3417 discover: Adjust CPU info obtained by Ollama under cgroup restrictions

📊 Changes

1 file changed (+48 additions, -0 deletions)

View changed files

📝 discover/gpu_linux.go (+48 -0)

📄 Description

When running Ollama inside Docker on machines with many CPUs, limiting the container’s CPU caused the number of threads Ollama spawns to mismatch the CPUs the container is allowed to use, significantly reducing inference performance. This commit slightly modifies Ollama to detect the number of CPUs the container is restricted to for better thread count alignment.

Note: Currently, this only supports CPU limits set via --cpuset-cpus; other limiting methods are not yet supported.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/12396 **Author:** [@dingdongxiangvolc](https://github.com/dingdongxiangvolc) **Created:** 9/24/2025 **Status:** 🔄 Open **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (1) - [`d9a3417`](https://github.com/ollama/ollama/commit/d9a341794184440c6173e494603d5bd9fc662bb9) discover: Adjust CPU info obtained by Ollama under cgroup restrictions ### 📊 Changes **1 file changed** (+48 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `discover/gpu_linux.go` (+48 -0) </details> ### 📄 Description When running Ollama inside Docker on machines with many CPUs, limiting the container’s CPU caused the number of threads Ollama spawns to mismatch the CPUs the container is allowed to use, significantly reducing inference performance. This commit slightly modifies Ollama to detect the number of CPUs the container is restricted to for better thread count alignment. Note: Currently, this only supports CPU limits set via --cpuset-cpus; other limiting methods are not yet supported. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2025-11-12 16:38:29 -06:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
windows
wsl
No Label pull-request
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-ollama#12547
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?