github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #12972] [MERGED] mac: fix stale VRAM data #14019

New Issue
Closed
opened 2026-04-13 00:42:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-13 00:42:42 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12972
Author: @dhiltgen
Created: 11/5/2025
Status: ✅ Merged
Merged: 11/5/2025
Merged by: @dhiltgen

Base: main ← Head: mac_refresh

📝 Commits (1)

📊 Changes

1 file changed (+2 additions, -2 deletions)

View changed files

📝 discover/runner.go (+2 -2)

📄 Description

The scheduler updates free VRAM based on current loaded models. This was mutating the persisted list of GPUs, and when coupled with the non-refreshing logic for Metal that lead to stale low VRAM reporting after unload. The fix is to make sure the GPU discovery always returns a copy so the schedulers GPU list is in fact ephemeral and doesn't leak any temporary adjustments back into the persistent list.

Fixes #12912

🔄 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/12972 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 11/5/2025 **Status:** ✅ Merged **Merged:** 11/5/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `mac_refresh` --- ### 📝 Commits (1) - [`8910237`](https://github.com/ollama/ollama/commit/8910237ed103bb8c4503367b9aa029ce78baaae8) mac: fix stale VRAM data ### 📊 Changes **1 file changed** (+2 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `discover/runner.go` (+2 -2) </details> ### 📄 Description The scheduler updates free VRAM based on current loaded models. This was mutating the persisted list of GPUs, and when coupled with the non-refreshing logic for Metal that lead to stale low VRAM reporting after unload. The fix is to make sure the GPU discovery always returns a copy so the schedulers GPU list is in fact ephemeral and doesn't leak any temporary adjustments back into the persistent list. Fixes #12912 --- <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 2026-04-13 00:42:42 -05:00
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 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#14019
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?