github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #15097] windows: avoid probing x64 cpu variant dlls on arm64 #77314

New Issue
Open
opened 2026-05-05 09:58:56 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 09:58:56 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15097
Author: @asadbek066
Created: 3/27/2026
Status: 🔄 Open

Base: main ← Head: fix/windows-arm64-cpu-dll-probing-15095

📝 Commits (1)

  • 47d905d windows: avoid probing x64 cpu variant dlls on arm64

📊 Changes

1 file changed (+42 additions, -0 deletions)

View changed files

📝 ml/backend/ggml/ggml/src/ggml-backend-reg.cpp (+42 -0)

📄 Description

Fixes #15095

On Windows ARM64, backend discovery probes CPU variant DLLs first (e.g. haswell/sse42/x64), which can trigger repeated wrong-architecture load failures.

This change detects Windows ARM64 and, for the CPU backend, loads the base ggml-cpu.dll directly instead of scanning CPU variant DLLs. That avoids loading x64 CPU variant DLLs on WoA and removes noisy load errors.

🔄 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/15097 **Author:** [@asadbek066](https://github.com/asadbek066) **Created:** 3/27/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `fix/windows-arm64-cpu-dll-probing-15095` --- ### 📝 Commits (1) - [`47d905d`](https://github.com/ollama/ollama/commit/47d905d973dedc8d8a3dd3a49b6d4bb8b68807a8) windows: avoid probing x64 cpu variant dlls on arm64 ### 📊 Changes **1 file changed** (+42 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `ml/backend/ggml/ggml/src/ggml-backend-reg.cpp` (+42 -0) </details> ### 📄 Description Fixes #15095 On Windows ARM64, backend discovery probes CPU variant DLLs first (e.g. haswell/sse42/x64), which can trigger repeated wrong-architecture load failures. This change detects Windows ARM64 and, for the CPU backend, loads the base `ggml-cpu.dll` directly instead of scanning CPU variant DLLs. That avoids loading x64 CPU variant DLLs on WoA and removes noisy load errors. --- <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 2026-05-05 09:58:56 -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#77314
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?