github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-09 11:22:14 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

[PR #5523] [MERGED] sched: don't error if paging to disk on Windows and macOS #10554

New Issue
Closed
opened 2025-11-12 15:31:13 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-12 15:31:13 -06:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/5523
Author: @jmorganca
Created: 7/7/2024
Status: ✅ Merged
Merged: 7/7/2024
Merged by: @jmorganca

Base: main ← Head: jmorganca/apple-silicon-no-error

📝 Commits (2)

  • 886672a sched: dont error if paging for macOS and Windows
  • ee20e02 add TODO for other OSes

📊 Changes

1 file changed (+24 additions, -13 deletions)

View changed files

📝 server/sched.go (+24 -13)

📄 Description

macOS and Windows don't error when paging to disk, so loosen this check for now to not return an error to users that could still run the model (albeit a little slowly). It also stops us from double counting memory on Apple Silicon Macs.

In the future, we should still select an upper limit on memory for macOS and Windows to avoid timeouts, etc. This PR is meant to unblock 0.1.49 and doesn't include that yet.

🔄 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/5523 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 7/7/2024 **Status:** ✅ Merged **Merged:** 7/7/2024 **Merged by:** [@jmorganca](https://github.com/jmorganca) **Base:** `main` ← **Head:** `jmorganca/apple-silicon-no-error` --- ### 📝 Commits (2) - [`886672a`](https://github.com/ollama/ollama/commit/886672a6b5dbaad917a28ded62dd7de10792ad04) sched: dont error if paging for macOS and Windows - [`ee20e02`](https://github.com/ollama/ollama/commit/ee20e0288b39f65e27a1a013d1a86d25dcc151b8) add TODO for other OSes ### 📊 Changes **1 file changed** (+24 additions, -13 deletions) <details> <summary>View changed files</summary> 📝 `server/sched.go` (+24 -13) </details> ### 📄 Description macOS and Windows don't error when paging to disk, so loosen this check for now to not return an error to users that could still run the model (albeit a little slowly). It also stops us from double counting memory on Apple Silicon Macs. In the future, we should still select an upper limit on memory for macOS and Windows to avoid timeouts, etc. This PR is meant to unblock 0.1.49 and doesn't include that yet. --- <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 15:31:13 -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#10554
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?