github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-27 16:36:54 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

Install script assumes existence of nvidia-smi on PATH means system uses Nvidia GPU #5655

New Issue
Open
opened 2025-11-12 13:05:47 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-12 13:05:47 -06:00
Owner
Copy Link

Originally created by @Gambloide on GitHub (Jan 30, 2025).

What is the issue?

My system has never seen an Nvidia GPU, but the current installer (https://ollama.com/install.sh) just finished on my system with the message "Nvidia GPU installed".

Actually executing nvidia-smi shows the same:

NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running.

From my understanding, rather than just checking if anything is available on the current PATH called nvidia-smi, it should actually try to confirm if a GPU from the given vendor is installed, otherwise ask the user to confirm/deny if unsure.

This is doubly important for multi-GPU or eGPU systems.

While off-topic, in case the question gets asked: No, I did not manually install Nvidia drivers on my system. I didn't even know they were there until just now when I looked into this bug. After uninstalling them, purging the old ollama install and running the script again, it correctly detected the AMD GPU and downloaded the ROCm amd64 bundle.

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.5.7

Originally created by @Gambloide on GitHub (Jan 30, 2025). ### What is the issue? My system has never seen an Nvidia GPU, but the current installer (https://ollama.com/install.sh) just finished on my system with the message "Nvidia GPU installed". Actually executing `nvidia-smi` shows the same: ``` NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running. ``` From my understanding, rather than just checking if anything is available on the current PATH called `nvidia-smi`, it should actually try to confirm if a GPU from the given vendor is installed, otherwise ask the user to confirm/deny if unsure. This is doubly important for multi-GPU or eGPU systems. --- **While off-topic, in case the question gets asked:** No, I did not manually install Nvidia drivers on my system. I didn't even know they were there until just now when I looked into this bug. After uninstalling them, purging the old ollama install and running the script again, it correctly detected the AMD GPU and downloaded the ROCm amd64 bundle. ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.5.7
GiteaMirror added the bug label 2025-11-12 13:05:47 -06:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
windows
wsl
No Label bug
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-ollama#5655
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?