c6d2f5918fbbd2b23a3c55f88e56e87fb4a5a09b
The old Dockerfile used the deprecated llama.cpp/ subdirectory approach which doesn't exist in ollama v0.23.2. Now using the official CMake presets (ROCm 6 preset) with AMDGPU_TARGETS including gfx906:xnack-.
Description
No description provided
Languages
Dockerfile
46.1%
Python
42%
Makefile
6.1%
Shell
5.8%