github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15510] Add flag to the install script to skip NVIDIA/CUDA and force Vulkan or CPU-only #56425

New Issue
Open
opened 2026-04-29 10:48:32 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 10:48:32 -05:00
Owner
Copy Link

Originally created by @linuxkernel94 on GitHub (Apr 11, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15510

Hi team,

I'm currently using Ollama on Linux and I've noticed that the current install.sh script automatically assumes an NVIDIA setup if it detects certain drivers or binaries, even when the user intends to use Vulkan or strictly CPU.

This often results in unnecessary downloads of heavy CUDA dependencies or installation failures when the environment doesn't perfectly match the script's detection logic.

Proposed Feature:
It would be extremely helpful to have a flag (e.g., --vulkan or --skip-nvidia) in the installer script to:

Manually select the backend: Force the installation of Vulkan-compatible libraries.

Minimize footprint: Avoid downloading several GBs of CUDA-related data when they aren't needed.

Improve Container Compatibility: Allow for cleaner installs in specialized environments like Fedora Silverblue (Toolbox) or SteamOS.

Example usage:
curl -fsSL https://ollama.com/install.sh | sh -s -- --vulkan

Having this level of control would greatly improve the experience for Linux users who are moving away from proprietary stacks or working in restricted environments.

Thanks for the amazing work on Ollama!

Originally created by @linuxkernel94 on GitHub (Apr 11, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15510 Hi team, I'm currently using Ollama on Linux and I've noticed that the current install.sh script automatically assumes an NVIDIA setup if it detects certain drivers or binaries, even when the user intends to use Vulkan or strictly CPU. This often results in unnecessary downloads of heavy CUDA dependencies or installation failures when the environment doesn't perfectly match the script's detection logic. Proposed Feature: It would be extremely helpful to have a flag (e.g., --vulkan or --skip-nvidia) in the installer script to: Manually select the backend: Force the installation of Vulkan-compatible libraries. Minimize footprint: Avoid downloading several GBs of CUDA-related data when they aren't needed. Improve Container Compatibility: Allow for cleaner installs in specialized environments like Fedora Silverblue (Toolbox) or SteamOS. Example usage: curl -fsSL https://ollama.com/install.sh | sh -s -- --vulkan Having this level of control would greatly improve the experience for Linux users who are moving away from proprietary stacks or working in restricted environments. Thanks for the amazing work on Ollama!
GiteaMirror added the feature request label 2026-04-29 10:48:33 -05:00
GiteaMirror commented 2026-04-29 10:48:36 -05:00
Author
Owner
Copy Link

@PureBlissAK commented on GitHub (Apr 18, 2026):

🤖 Automated Triage & Analysis Report

Issue: #15510
Analyzed: 2026-04-18T18:21:24.857432

Analysis

  • Type: unknown
  • Severity: medium
  • Components: unknown

Implementation Plan

  • Effort: medium
  • Steps:

This issue has been triaged and marked for implementation.

<!-- gh-comment-id:4274308254 --> @PureBlissAK commented on GitHub (Apr 18, 2026): <!-- ollama-issue-orchestrator:v1 issue:15510 --> ## 🤖 Automated Triage & Analysis Report **Issue**: #15510 **Analyzed**: 2026-04-18T18:21:24.857432 ### Analysis - **Type**: unknown - **Severity**: medium - **Components**: unknown ### Implementation Plan - **Effort**: medium - **Steps**: *This issue has been triaged and marked for implementation.*
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#56425
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?