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

[GH-ISSUE #2034] Not running on gpu #26935

New Issue
Closed
opened 2026-04-22 03:43:49 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 03:43:49 -05:00
Owner
Copy Link

Originally created by @DragonBtc93 on GitHub (Jan 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2034

I'm a Ubuntu 22.04 use have a Nvidia tesla p40 and a k80 gpu and it will not use gpu. I can use text generation webui and get gpu.

Originally created by @DragonBtc93 on GitHub (Jan 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2034 I'm a Ubuntu 22.04 use have a Nvidia tesla p40 and a k80 gpu and it will not use gpu. I can use text generation webui and get gpu.
GiteaMirror commented 2026-04-22 03:43:51 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 26, 2024):

Assuming these are in the same system, the K80 is the problem. That GPU is a Compute Capability 3.7 card, while the P40 is a Compute Capability 6.1 card. 6.1 is supported today, but 3.5 is not yet supported, and tracked via issue #1756
We don't yet have a solid way to ignore unsupported cards and use supported cards, so we'll disable GPU mode if we detect any GPU that isn't supported. As a workaround until we fix #1756, you can pull the K80 and Ollama should run on the P40 GPU.

https://developer.nvidia.com/cuda-gpus

<!-- gh-comment-id:1912710243 --> @dhiltgen commented on GitHub (Jan 26, 2024): Assuming these are in the same system, the K80 is the problem. That GPU is a Compute Capability 3.7 card, while the P40 is a Compute Capability 6.1 card. 6.1 is supported today, but 3.5 is not yet supported, and tracked via issue #1756 We don't yet have a solid way to ignore unsupported cards and use supported cards, so we'll disable GPU mode if we detect any GPU that isn't supported. As a workaround until we fix #1756, you can pull the K80 and Ollama should run on the P40 GPU. https://developer.nvidia.com/cuda-gpus
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
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#26935
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?