github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #1059] [MERGED] skip gpu if less than 2GB VRAM are available #15723

New Issue
Closed
opened 2026-04-16 05:05:55 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 05:05:55 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/1059
Author: @BruceMacD
Created: 11/9/2023
Status: ✅ Merged
Merged: 11/9/2023
Merged by: @BruceMacD

Base: main ← Head: brucemacd/gpu-failover

📝 Commits (1)

  • 01c219e skip gpu if less than 2GB VRAM are available

📊 Changes

1 file changed (+8 additions, -5 deletions)

View changed files

📝 llm/llama.go (+8 -5)

📄 Description

This check for available VRAM that triggered a fallback to CPU if less than 2GB of VRAM was available wasn't handled correctly in the current ollama version. This resulted in a very low amount of layers being offloaded to GPU in the case that a GPU was available with a low amount of available VRAM, and this results in worse performance than just falling back to CPU.

🔄 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/1059 **Author:** [@BruceMacD](https://github.com/BruceMacD) **Created:** 11/9/2023 **Status:** ✅ Merged **Merged:** 11/9/2023 **Merged by:** [@BruceMacD](https://github.com/BruceMacD) **Base:** `main` ← **Head:** `brucemacd/gpu-failover` --- ### 📝 Commits (1) - [`01c219e`](https://github.com/ollama/ollama/commit/01c219ee887faaabbd11760df6d7f6cbba57d0f7) skip gpu if less than 2GB VRAM are available ### 📊 Changes **1 file changed** (+8 additions, -5 deletions) <details> <summary>View changed files</summary> 📝 `llm/llama.go` (+8 -5) </details> ### 📄 Description This check for available VRAM that triggered a fallback to CPU if less than 2GB of VRAM was available wasn't handled correctly in the current ollama version. This resulted in a very low amount of layers being offloaded to GPU in the case that a GPU was available with a low amount of available VRAM, and this results in worse performance than just falling back to CPU. --- <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 2026-04-16 05:05:55 -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#15723
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?