github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #2585] [MERGED] Fix cuda leaks #10938

New Issue
Closed
opened 2026-04-12 23:16:13 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 23:16:13 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/2585
Author: @dhiltgen
Created: 2/19/2024
Status: ✅ Merged
Merged: 2/19/2024
Merged by: @dhiltgen

Base: main ← Head: cuda_leaks

📝 Commits (1)

📊 Changes

2 files changed (+136 additions, -9 deletions)

View changed files

📝 llm/patches/02-shutdown.diff (+20 -9)
➕ llm/patches/03-cudaleaks.diff (+116 -0)

📄 Description

This should resolve the problem where we don't fully unload from the GPU when we go idle.

Fixes #1848

This carries the upstream PR https://github.com/ggerganov/llama.cpp/pull/5576 as a patch until that's reviewed/merged.

This also updates the shutdown patch to match what was merged upstream since we haven't yet bumped llama.cpp to pick that up.

🔄 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/2585 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 2/19/2024 **Status:** ✅ Merged **Merged:** 2/19/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `cuda_leaks` --- ### 📝 Commits (1) - [`fc39a6c`](https://github.com/ollama/ollama/commit/fc39a6cd7a5f9a4951babb183826f15eea0351ff) Fix cuda leaks ### 📊 Changes **2 files changed** (+136 additions, -9 deletions) <details> <summary>View changed files</summary> 📝 `llm/patches/02-shutdown.diff` (+20 -9) ➕ `llm/patches/03-cudaleaks.diff` (+116 -0) </details> ### 📄 Description This should resolve the problem where we don't fully unload from the GPU when we go idle. Fixes #1848 This carries the upstream PR https://github.com/ggerganov/llama.cpp/pull/5576 as a patch until that's reviewed/merged. This also updates the shutdown patch to match what was [merged upstream](https://github.com/ggerganov/llama.cpp/pull/5244#pullrequestreview-1887279675) since we haven't yet bumped llama.cpp to pick that up. --- <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 2026-04-12 23:16:13 -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#10938
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?