From 57270767ac5d4e6686a34c01e7045c397dc95d1c Mon Sep 17 00:00:00 2001 From: Thomas Stocker Date: Sat, 9 Aug 2025 22:26:54 +0200 Subject: [PATCH] Remove flashattention setting gpu.go --- discover/gpu.go | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/discover/gpu.go b/discover/gpu.go index 842e817c6..f76e2abf1 100644 --- a/discover/gpu.go +++ b/discover/gpu.go @@ -309,8 +309,7 @@ func GetGPUInfo() GpuInfoList { slog.Info("error looking up nvidia GPU memory", "error", C.GoString(memInfo.err)) C.free(unsafe.Pointer(memInfo.err)) continue - } - gpuInfo.FlashAttention = driverMajor >= 7 + } gpuInfo.TotalMemory = uint64(memInfo.total) gpuInfo.FreeMemory = uint64(memInfo.free) gpuInfo.ID = C.GoString(&memInfo.gpu_id[0]) @@ -394,8 +393,7 @@ func GetGPUInfo() GpuInfoList { C.oneapi_check_vram(*oHandles.oneapi, C.int(d), i, &memInfo) // TODO - convert this to MinimumMemory based on testing... var totalFreeMem float64 = float64(memInfo.free) * 0.95 // work-around: leave some reserve vram for mkl lib used in ggml-sycl backend. - memInfo.free = C.uint64_t(totalFreeMem) - gpuInfo.FlashAttention = false + memInfo.free = C.uint64_t(totalFreeMem) gpuInfo.TotalMemory = uint64(memInfo.total) gpuInfo.FreeMemory = uint64(memInfo.free) gpuInfo.ID = C.GoString(&memInfo.gpu_id[0]) @@ -424,8 +422,7 @@ func GetGPUInfo() GpuInfoList { C.free(unsafe.Pointer(memInfo.err)) continue } - - gpuInfo.FlashAttention = (C.vk_check_flash_attention(*vHandles.vulkan, C.int(i)) == 0) // 0 means supported + gpuInfo.TotalMemory = uint64(memInfo.total) gpuInfo.FreeMemory = uint64(memInfo.free) gpuInfo.ID = C.GoString(&memInfo.gpu_id[0])