#18502·ollama

linux: fix Vulkan inference support on ARM64 (PR implemented)

Author: alandoozCreated Sep 17, 2026Updated Sep 17, 2026
Labelsbug

What is the issue?

The Linux ARM64 Docker image currently does not include the Vulkan backend, even though Vulkan support is enabled at runtime. This causes Vulkan-capable ARM64 systems to fall back to CPU inference.

Tested in ARM64 Apple Silicon M1 running Asahi Linux.

This PR fixes that.

Relevant log output

OS

Linux

GPU

Apple

CPU

No response

Ollama version

0.34.1