diff options
| author | Henry J. Webster <hwebs@hwebs.info> | 2026-08-03 21:38:08 -0500 |
|---|---|---|
| committer | Henry J. Webster <hwebs@hwebs.info> | 2026-08-03 21:39:51 -0500 |
| commit | 71e36370770acc7498748a890cd0365b3d351027 (patch) | |
| tree | 60c4180135368f928bdc651f7b5d769886c56441 /flake.lock | |
| parent | e9b9671d238bb3de779c0dbf4a518b41280be778 (diff) | |
kusanagi/ollama: fix ROCm GPU fallback to CPU for Gemma
The RDNA3 card reports as gfx1101/gfx1102/gfx11-generic, which the ROCm
build bundled with ollama-rocm has no kernels for, so ollama found no
usable device and ran 100% on CPU after the nixpkgs bump. Force it to
present as gfx1100 via HSA_OVERRIDE_GFX_VERSION.
Also set OLLAMA_FLASH_ATTENTION=1 so the existing q8_0 KV cache actually
engages instead of silently falling back to f16 and inflating VRAM use.
Assisted-by: Claude-code:Opus-4.8
Diffstat (limited to 'flake.lock')
0 files changed, 0 insertions, 0 deletions