discover: CPU supports flash attention

We already run flash attention on CPUs in cases where we have
partial offloading but were disabling it if running on pure CPU,
 which is unnecessary.
This commit is contained in:
Jesse Gross
2025-08-11 14:45:45 -07:00
committed by Jesse Gross
parent dbfd7bd027
commit 8f4ec9ab28

View File

@@ -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"