diff --git a/discover/types.go b/discover/types.go index c5212d94e0..13a030fd59 100644 --- a/discover/types.go +++ b/discover/types.go @@ -171,7 +171,8 @@ func (si SystemInfo) GetOptimalThreadCount() int { // For each GPU, check if it does NOT support flash attention func (l GpuInfoList) FlashAttentionSupported() bool { for _, gpu := range l { - supportsFA := gpu.Library == "metal" || + supportsFA := gpu.Library == "cpu" || + gpu.Library == "metal" || (gpu.Library == "cuda" && gpu.DriverMajor >= 7) || gpu.Library == "rocm"