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_test.go

llm: Don't always evict models on CPU-only systems

2025-12-02 10:58:08 -08:00

server.go

gemma4: Disable FA on older GPUs where it doesn't work (#15403)

2026-04-07 14:54:25 -07:00

status.go

logs: catch rocm errors (#12888)

2025-10-31 09:54:25 -07:00