github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12848] Vulkan device selection #34273

New Issue
Closed
opened 2026-04-22 17:42:50 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 17:42:50 -05:00
Owner
Copy Link

Originally created by @saeedtahmtan on GitHub (Oct 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12848

Originally assigned to: @dhiltgen on GitHub.

Can't select Vulkan device in the ollama

[Service]
Environment="MESA_VK_DEVICE_SELECT=1"

environment variable also ignored.

Originally created by @saeedtahmtan on GitHub (Oct 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12848 Originally assigned to: @dhiltgen on GitHub. Can't select Vulkan device in the ollama ```ini [Service] Environment="MESA_VK_DEVICE_SELECT=1" ``` environment variable also ignored.
GiteaMirror added the feature request label 2026-04-22 17:42:50 -05:00
GiteaMirror commented 2026-04-22 17:42:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 30, 2025):

GGML_VK_VISIBLE_DEVICES

<!-- gh-comment-id:3467138661 --> @rick-github commented on GitHub (Oct 30, 2025): [`GGML_VK_VISIBLE_DEVICES`](https://github.com/ollama/ollama/blob/0a2d92081bb6b6b2d3eab5908fce08cfcf736e1d/envconfig/config.go#L314)
GiteaMirror commented 2026-04-22 17:42:54 -05:00
Author
Owner
Copy Link

@saeedtahmtan commented on GitHub (Oct 30, 2025):

that is the right answer and thank you. I wander if we could keep the device but sort them or use one as primary to utilize both of my GPU integrated and dedicated it slow for one model but might be fast for running two model parallel to each other.

I might found an idea for that to have two instance of Ollama and each have separate GGML_VK_VISIBLE_DEVICES

<!-- gh-comment-id:3469290368 --> @saeedtahmtan commented on GitHub (Oct 30, 2025): that is the right answer and thank you. I wander if we could keep the device but sort them or use one as primary to utilize both of my GPU integrated and dedicated it slow for one model but might be fast for running two model parallel to each other. I might found an idea for that to have two instance of Ollama and each have separate GGML_VK_VISIBLE_DEVICES
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#34273
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?