github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 14:13:13 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9386] How to check the cuda is working with docker #83809

New Issue
Closed
opened 2026-05-09 19:06:06 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-09 19:06:06 -05:00
Owner
Copy Link

Originally created by @ROBODRILL on GitHub (Feb 27, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9386

I install the ollama and model in an images.I check the GPU with the command "nvidia-smi" ,it works.then I check the CUDA with the command "nvcc --version" ,the system show me "command not found".
So ,what should I do?
Thank you ,guys

Originally created by @ROBODRILL on GitHub (Feb 27, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9386 I install the ollama and model in an images.I check the GPU with the command "nvidia-smi" ,it works.then I check the CUDA with the command "nvcc --version" ,the system show me "command not found". So ,what should I do? Thank you ,guys
GiteaMirror added the feature request label 2026-05-09 19:06:06 -05:00
GiteaMirror commented 2026-05-09 19:06:08 -05:00
Author
Owner
Copy Link

@j820301 commented on GitHub (Feb 27, 2025):

The nvidia-smi command is a driver command, while the nvcc --version command is a Toolkit command that requires the installation of the Toolkit to produce output. As for whether Ollama needs to install the Toolkit for support, I'm not sure yet. However, I can run it with just the driver installed, and I'm unsure about the differences in execution. I hope someone else can provide further explanation.

<!-- gh-comment-id:2686791648 --> @j820301 commented on GitHub (Feb 27, 2025): The nvidia-smi command is a driver command, while the nvcc --version command is a [Toolkit](https://developer.nvidia.com/cuda-12-5-1-download-archive?target_os=Linux&target_arch=x86_64&Distribution=Ubuntu&target_version=24.04&target_type=deb_network) command that requires the installation of the Toolkit to produce output. As for whether Ollama needs to install the Toolkit for support, I'm not sure yet. However, I can run it with just the driver installed, and I'm unsure about the differences in execution. I hope someone else can provide further explanation.
GiteaMirror commented 2026-05-09 19:06:08 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 9, 2026):

nvidia-smi is enough to verify that the GPU is available to ollama from within a container.

<!-- gh-comment-id:3873200142 --> @rick-github commented on GitHub (Feb 9, 2026): `nvidia-smi` is enough to verify that the GPU is available to ollama from within a container.
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 feature 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#83809
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?