- 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