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 #12108] [MERGED] Always filter devices #24249

New Issue
Closed
opened 2026-04-19 17:28:14 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 17:28:14 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12108
Author: @dhiltgen
Created: 8/28/2025
Status: ✅ Merged
Merged: 8/29/2025
Merged by: @dhiltgen

Base: main ← Head: igpu_crash

📝 Commits (2)

📊 Changes

8 files changed (+65 additions, -70 deletions)

View changed files

📝 discover/amd_linux.go (+14 -6)
📝 discover/amd_windows.go (+13 -5)
📝 discover/cuda_common.go (+0 -13)
📝 discover/gpu.go (+16 -14)
📝 discover/gpu_darwin.go (+2 -2)
➖ discover/gpu_oneapi.go (+0 -21)
📝 discover/types.go (+6 -5)
📝 llm/server.go (+14 -4)

📄 Description

Avoid crashing on unsupported AMD iGPUs

Also fixes a bug where the env workarounds weren't ported over to the new loading code correctly.

This code will get refactored pretty heavily with #12090 but that's not quite ready yet, so this should be a minimal fix to the AMD iGPU crashes some users are facing.

Fixes #11975

Draft until I can verify on a few test systems.

🔄 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/12108 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 8/28/2025 **Status:** ✅ Merged **Merged:** 8/29/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `igpu_crash` --- ### 📝 Commits (2) - [`3b395b3`](https://github.com/ollama/ollama/commit/3b395b375d5b6af265a6cfeaab84b6caea5a2160) Always filter devices - [`0c52783`](https://github.com/ollama/ollama/commit/0c52783f20db29f23aa4cbd098aebea98b412d90) Remove cuda device filtering ### 📊 Changes **8 files changed** (+65 additions, -70 deletions) <details> <summary>View changed files</summary> 📝 `discover/amd_linux.go` (+14 -6) 📝 `discover/amd_windows.go` (+13 -5) 📝 `discover/cuda_common.go` (+0 -13) 📝 `discover/gpu.go` (+16 -14) 📝 `discover/gpu_darwin.go` (+2 -2) ➖ `discover/gpu_oneapi.go` (+0 -21) 📝 `discover/types.go` (+6 -5) 📝 `llm/server.go` (+14 -4) </details> ### 📄 Description Avoid crashing on unsupported AMD iGPUs Also fixes a bug where the env workarounds weren't ported over to the new loading code correctly. This code will get refactored pretty heavily with #12090 but that's not quite ready yet, so this should be a minimal fix to the AMD iGPU crashes some users are facing. Fixes #11975 Draft until I can verify on a few test systems. --- <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 17:28:14 -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#24249
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?