ollama/llm
Daniel Hiltgen dde09129d1
gemma4: Disable FA on older GPUs where it doesn't work (#15403)
CUDA older than 7.5 lack the support to enable flash attention for the model.
2026-04-07 14:54:25 -07:00
..
llm_darwin.go Optimize container images for startup (#6547) 2024-09-12 12:10:30 -07:00
llm_linux.go Optimize container images for startup (#6547) 2024-09-12 12:10:30 -07:00
llm_windows.go win: lint fix (#10571) 2025-05-05 11:08:12 -07:00
server.go gemma4: Disable FA on older GPUs where it doesn't work (#15403) 2026-04-07 14:54:25 -07:00
server_test.go llm: Don't always evict models on CPU-only systems 2025-12-02 10:58:08 -08:00
status.go logs: catch rocm errors (#12888) 2025-10-31 09:54:25 -07:00