Hermes c6d2f5918f fix: use ollama v0.23.2 native CMake build system for ROCm 6 + gfx906
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-.
2026-05-09 22:13:47 -04:00
2025-08-08 15:08:10 -04:00
Description
No description provided
878 KiB
Languages
Dockerfile 46.1%
Python 42%
Makefile 6.1%
Shell 5.8%