github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8399] unable to use nvidia GPU & how to fix #5395

New Issue
Closed
opened 2026-04-12 16:37:38 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 16:37:38 -05:00
Owner
Copy Link

Originally created by @belmont on GitHub (Jan 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8399

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I have been suffering 3 hours this morning to make nvidia work with ollama fresh install. Whatever model i tried It did not use the nvidia H100 GPUs even if the systemctl status ollama is nicely showing the GPUs. For this you need to install nvidia toolkit. I have picked the latest of driver, toolkit, cuda and ollama did not load in the GPUs. Then i discovered I dont have the AVX enabled in my CPU of the VM. So, i said, its really good to have, so i enabled it and BINGO !!!! , ollama got loaded into the GPU!! Now all good!!

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.4

Originally created by @belmont on GitHub (Jan 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8399 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I have been suffering 3 hours this morning to make nvidia work with ollama fresh install. Whatever model i tried It did not use the nvidia H100 GPUs even if the systemctl status ollama is nicely showing the GPUs. For this you need to install nvidia toolkit. I have picked the latest of driver, toolkit, cuda and ollama did not load in the GPUs. Then i discovered I dont have the AVX enabled in my CPU of the VM. So, i said, its really good to have, so i enabled it and BINGO !!!! , ollama got loaded into the GPU!! Now all good!! ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.4
GiteaMirror added the gpubug labels 2026-04-12 16:37:38 -05:00
GiteaMirror commented 2026-04-12 16:37:40 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 15, 2025):

It sounds like we can probably close this issue now.

We're working on improvements that will enable more permutations of CPU vector flags for GPU runners in a future version. Until then https://github.com/ollama/ollama/blob/main/docs/development.md#advanced-cpu-vector-settings documents how to build from source with customized settings.

<!-- gh-comment-id:2594153654 --> @dhiltgen commented on GitHub (Jan 15, 2025): It sounds like we can probably close this issue now. We're working on improvements that will enable more permutations of CPU vector flags for GPU runners in a future version. Until then https://github.com/ollama/ollama/blob/main/docs/development.md#advanced-cpu-vector-settings documents how to build from source with customized settings.
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 bug gpu
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#5395
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?