ef5815589782ed30f7273c2ccb7a423730f9f68d
- Add ollama/Dockerfile that builds ollama from source with AMDGPU_TARGETS=gfx906 - Uses ROCm 6.1 (rocm/dev-ubuntu-22.04:6.1.2-complete) for MI50 support - Builds llama.cpp runner with HIPBLAS for gfx906 architecture - Updates compose.yml to build from this Dockerfile instead of pulling ollama/ollama:latest
Description
No description provided
Languages
Dockerfile
46.1%
Python
42%
Makefile
6.1%
Shell
5.8%