github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5652] A path to GPU support for Ollama in a VM/container on Apple Silicon #50037

New Issue
Open
opened 2026-04-28 13:55:06 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 13:55:06 -05:00
Owner
Copy Link

Originally created by @easp on GitHub (Jul 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5652

I came across a short discussion in the llama.cpp repo about using a GPU on Apple Silicon from within a vm/container. Performance isn't as good as bare metal, but it's a significant improvement over CPU-only inference.

The meat of it is this work from March which provides a virtualized Vulkan interface inside the VM which is then passed-through to a vulkan-to-metal layer on the host MacOS.

For this to be relevant to Ollama I think it would require this proof of concept work with podman to be implemented in Docker Desktop for Mac, but I'm noting it here because it shows a way forward.

Originally created by @easp on GitHub (Jul 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5652 I came across a short discussion in the llama.cpp repo about using a [GPU on Apple Silicon from within a vm/container](https://github.com/ggerganov/llama.cpp/discussions/8042). Performance isn't as good as bare metal, but it's a significant improvement over CPU-only inference. The meat of it is [this work](https://sinrega.org/2024-03-06-enabling-containers-gpu-macos/) from March which provides a virtualized Vulkan interface inside the VM which is then passed-through to a vulkan-to-metal layer on the host MacOS. For this to be relevant to Ollama I think it would require this proof of concept work with podman to be implemented in Docker Desktop for Mac, but I'm noting it here because it shows a way forward.
GiteaMirror added the feature request label 2026-04-28 13:55:06 -05:00
GiteaMirror commented 2026-04-28 13:55:12 -05:00
Author
Owner
Copy Link

@hybra commented on GitHub (Jul 15, 2024):

Have a look:
https://github.com/ggerganov/llama.cpp/discussions/8042#discussioncomment-10044780

<!-- gh-comment-id:2229190932 --> @hybra commented on GitHub (Jul 15, 2024): Have a look: https://github.com/ggerganov/llama.cpp/discussions/8042#discussioncomment-10044780
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#50037
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?