pali112
/
ollama
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Enable Vulkan Flash attention in FlashAttentionSupported

This commit is contained in:
Inforithmics 2025-08-12 21:55:19 +02:00
parent e6da524ab7
commit 49c4d154ae
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
discover/gpu.go
View File

@ -422,8 +422,7 @@ func GetGPUInfo() GpuInfoList {
C.free(unsafe.Pointer(memInfo.err))
continue
}
gpuInfo.FlashAttention = true
gpuInfo.TotalMemory = uint64(memInfo.total)
gpuInfo.FreeMemory = uint64(memInfo.free)
gpuInfo.ID = C.GoString(&memInfo.gpu_id[0])

3
discover/types.go
View File

@ -182,7 +182,8 @@ func (l GpuInfoList) FlashAttentionSupported() bool {
supportsFA := gpu.Library == "cpu" ||
gpu.Library == "metal" ||
(gpu.Library == "cuda" && gpu.DriverMajor >= 7) ||
gpu.Library == "rocm"
gpu.Library == "rocm" ||
gpu.Library == "vulkan"
if !supportsFA {
return false