github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 05:36:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #15000] add MoltenVK support for Intel macs #25501

New Issue
Open
opened 2026-04-19 18:15:06 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 18:15:06 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15000
Author: @jamfor999
Created: 3/22/2026
Status: 🔄 Open

Base: main ← Head: dev

📝 Commits (2)

  • 2e3a77e cmake: add experimental MoltenVK support for Intel Mac AMD GPUs
  • b5452b8 cmake: pin MoltenVK to v1.4.1

📊 Changes

5 files changed (+430 additions, -12 deletions)

View changed files

📝 CMakeLists.txt (+26 -12)
📝 CMakePresets.json (+12 -0)
📝 README.md (+19 -0)
➕ cmake/OllamaMoltenVK.cmake (+135 -0)
➕ scripts/build_darwin_vulkan.sh (+238 -0)

📄 Description

Created this fork a while back as part of this issue: https://github.com/ollama/ollama/issues/1016

There are still users of Intel Macs with AMD GPUs and while macOS support for Intel machines is being deprecated by Apple, these machines still exist and will stay in use. people still like to use macOS, and it will still have Security support for quite a while (plus I highly suspect it'll live on some way or another, although thats a whole other thing...)

Seems like users are happy with my fork, its had a number of stars and no real reported issues over the past few months, so I'm happy to contribute this upstream at this stage, it should not cause issues for other users.

Note: even if this is merged in no way does this mean Ollama will need to produce binaries,
but it means people will be able to build it if they want it from source while ensuring it'll stay synced with upstream.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/15000 **Author:** [@jamfor999](https://github.com/jamfor999) **Created:** 3/22/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `dev` --- ### 📝 Commits (2) - [`2e3a77e`](https://github.com/ollama/ollama/commit/2e3a77e7e92badefb4d3217f3200f503cb7172c0) cmake: add experimental MoltenVK support for Intel Mac AMD GPUs - [`b5452b8`](https://github.com/ollama/ollama/commit/b5452b8577bb8e256d34d9167180df15fe66db53) cmake: pin MoltenVK to v1.4.1 ### 📊 Changes **5 files changed** (+430 additions, -12 deletions) <details> <summary>View changed files</summary> 📝 `CMakeLists.txt` (+26 -12) 📝 `CMakePresets.json` (+12 -0) 📝 `README.md` (+19 -0) ➕ `cmake/OllamaMoltenVK.cmake` (+135 -0) ➕ `scripts/build_darwin_vulkan.sh` (+238 -0) </details> ### 📄 Description Created this fork a while back as part of this issue: https://github.com/ollama/ollama/issues/1016 There are still users of Intel Macs with AMD GPUs and while macOS support for Intel machines is being deprecated by Apple, these machines still exist and will stay in use. people still like to use macOS, and it will still have Security support for quite a while (plus I highly suspect it'll live on some way or another, although thats a whole other thing...) Seems like users are happy with my fork, its had a number of stars and no real reported issues over the past few months, so I'm happy to contribute this upstream at this stage, it should not cause issues for other users. Note: even if this is merged in no way does this mean Ollama will need to produce binaries, but it means people will be able to build it if they want it from source while ensuring it'll stay synced with upstream. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-19 18:15:06 -05:00
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 pull-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#25501
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?