github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #15383] x/imagegen/mlx: this fix stops ollama from failing to initialise when running on non-mlx supported hardware, it can continue with CPU #41007

New Issue
Open
opened 2026-04-23 01:45:51 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-23 01:45:51 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15383
Author: @liams000
Created: 4/7/2026
Status: 🔄 Open

Base: main ← Head: fix-mlx-init-on-non-mlx-supported-systems

📝 Commits (1)

  • adea759 x/imagegen/mlx: this fix stops ollama from failing to initialise when running on non-mlx supported hardware, it can continue with CPU

📊 Changes

1 file changed (+5 additions, -0 deletions)

View changed files

📝 x/imagegen/mlx/mlx.go (+5 -0)

📄 Description

Issue: #15253

My computer is a windows machine running on an AMD CPU and an AMD Radeon RX 6750 XT, I am blessed with not having CUDA and running into problems when running local LLMs. Recently I downloaded Ollama and ran into the issue that I couldn't even get the command to return anything without instantly getting the bellow error:

Exception 0xc0000005 0x8 0xffffffffffffffff 0xffffffffffffffff
PC=0xffffffffffffffff
signal arrived during external code execution

runtime.cgocall(0x7ff654cb1790, 0xc00004dda0)
        runtime/cgocall.go:167 +0x3e fp=0xc00004dd78 sp=0xc00004dd10 pc=0x7ff653b8243e
github.com/ollama/ollama/x/imagegen/mlx._Cfunc_mlx_random_key(0xc0000962e0, 0x19d6747566d)
        _cgo_gotypes.go:1978 +0x50 fp=0xc00004dda0 sp=0xc00004dd78 pc=0x7ff654210930
github.com/ollama/ollama/x/imagegen/mlx.RandomKey.func1(...)
        github.com/ollama/ollama/x/imagegen/mlx/mlx.go:1870
github.com/ollama/ollama/x/imagegen/mlx.RandomKey(0x19d6747566d)
        github.com/ollama/ollama/x/imagegen/mlx/mlx.go:1870 +0x5d fp=0xc00004ddd8 sp=0xc00004dda0 pc=0x7ff65421985d
github.com/ollama/ollama/x/imagegen/mlx.init.0()
        github.com/ollama/ollama/x/imagegen/mlx/mlx.go:1848 +0xa9 fp=0xc00004de28 sp=0xc00004ddd8 pc=0x7ff654219669
runtime.doInit1(0x7ff6560412c0)
        runtime/proc.go:7350 +0xdd fp=0xc00004df50 sp=0xc00004de28 pc=0x7ff653b6343d
runtime.doInit(...)
        runtime/proc.go:7317
runtime.main()
        runtime/proc.go:254 +0x325 fp=0xc00004dfe0 sp=0xc00004df50 pc=0x7ff653b54e85
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00004dfe8 sp=0xc00004dfe0 pc=0x7ff653b8db21

The change I am proposing, protects the usage of the MLX lib in the event that it didn't happen to throw an error at time of init. Returning and continuing on should be ok as the application should fall back to using CPU in this scenario.

This fixes the issues some users have been recently experiencing.

🔄 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/15383 **Author:** [@liams000](https://github.com/liams000) **Created:** 4/7/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `fix-mlx-init-on-non-mlx-supported-systems` --- ### 📝 Commits (1) - [`adea759`](https://github.com/ollama/ollama/commit/adea759a66b30eb4ca18cf5bc9c491c55a5ebf83) x/imagegen/mlx: this fix stops ollama from failing to initialise when running on non-mlx supported hardware, it can continue with CPU ### 📊 Changes **1 file changed** (+5 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `x/imagegen/mlx/mlx.go` (+5 -0) </details> ### 📄 Description Issue: [#15253](https://github.com/ollama/ollama/issues/15253) My computer is a windows machine running on an AMD CPU and an AMD Radeon RX 6750 XT, I am blessed with not having CUDA and running into problems when running local LLMs. Recently I downloaded Ollama and ran into the issue that I couldn't even get the command to return anything without instantly getting the bellow error: ```ps1 Exception 0xc0000005 0x8 0xffffffffffffffff 0xffffffffffffffff PC=0xffffffffffffffff signal arrived during external code execution runtime.cgocall(0x7ff654cb1790, 0xc00004dda0) runtime/cgocall.go:167 +0x3e fp=0xc00004dd78 sp=0xc00004dd10 pc=0x7ff653b8243e github.com/ollama/ollama/x/imagegen/mlx._Cfunc_mlx_random_key(0xc0000962e0, 0x19d6747566d) _cgo_gotypes.go:1978 +0x50 fp=0xc00004dda0 sp=0xc00004dd78 pc=0x7ff654210930 github.com/ollama/ollama/x/imagegen/mlx.RandomKey.func1(...) github.com/ollama/ollama/x/imagegen/mlx/mlx.go:1870 github.com/ollama/ollama/x/imagegen/mlx.RandomKey(0x19d6747566d) github.com/ollama/ollama/x/imagegen/mlx/mlx.go:1870 +0x5d fp=0xc00004ddd8 sp=0xc00004dda0 pc=0x7ff65421985d github.com/ollama/ollama/x/imagegen/mlx.init.0() github.com/ollama/ollama/x/imagegen/mlx/mlx.go:1848 +0xa9 fp=0xc00004de28 sp=0xc00004ddd8 pc=0x7ff654219669 runtime.doInit1(0x7ff6560412c0) runtime/proc.go:7350 +0xdd fp=0xc00004df50 sp=0xc00004de28 pc=0x7ff653b6343d runtime.doInit(...) runtime/proc.go:7317 runtime.main() runtime/proc.go:254 +0x325 fp=0xc00004dfe0 sp=0xc00004df50 pc=0x7ff653b54e85 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00004dfe8 sp=0xc00004dfe0 pc=0x7ff653b8db21 ``` The change I am proposing, protects the usage of the MLX lib in the event that it didn't happen to throw an error at time of init. Returning and continuing on should be ok as the application should fall back to using CPU in this scenario. This fixes the issues some users have been recently experiencing. --- <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 2026-04-23 01:45:51 -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#41007
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?