ggml: avoid creating CUDA context during device init (llama/20595)

diff --git a/src/ggml-cuda/ggml-cuda.cu b/src/ggml-cuda/ggml-cuda.cu
index 3886290c5ff9c8fa9ee9a61f8006fb58f692062f..5a0be4a472a5f25a40ea4c85466c669fcd9b477e 100644 (file)
--- a/src/ggml-cuda/ggml-cuda.cu
+++ b/src/ggml-cuda/ggml-cuda.cu
@@ -254,11 +254,6 @@ static ggml_cuda_device_info ggml_cuda_init() {
         info.devices[id].supports_cooperative_launch = false;
 #endif // !(GGML_USE_MUSA)
 
-        // cudaMemGetInfo returns info for the current device
-        size_t free_mem;
-        CUDA_CHECK(cudaSetDevice(id));
-        CUDA_CHECK(cudaMemGetInfo(&free_mem, NULL));
-
 #if defined(GGML_USE_HIP)
         info.devices[id].smpbo = prop.sharedMemPerBlock;
 
@@ -273,25 +268,25 @@ static ggml_cuda_device_info ggml_cuda_init() {
                 info.devices[id].cc += prop.minor * 0x10;
             }
         }
-        GGML_LOG_INFO("  Device %d: %s, %s (0x%x), VMM: %s, Wave Size: %d, VRAM: %zu MiB (%zu MiB free)\n",
+        GGML_LOG_INFO("  Device %d: %s, %s (0x%x), VMM: %s, Wave Size: %d, VRAM: %zu MiB\n",
                       id, prop.name, prop.gcnArchName, info.devices[id].cc & 0xffff,
                       device_vmm ? "yes" : "no", prop.warpSize,
-                      (size_t)(prop.totalGlobalMem / (1024 * 1024)), free_mem / (1024 * 1024));
+                      (size_t)(prop.totalGlobalMem / (1024 * 1024)));
 #elif defined(GGML_USE_MUSA)
         // FIXME: Ensure compatibility with varying warp sizes across different MUSA archs.
         info.devices[id].warp_size = 32;
         info.devices[id].smpbo = prop.sharedMemPerBlockOptin;
         info.devices[id].cc = GGML_CUDA_CC_OFFSET_MTHREADS + prop.major * 0x100;
         info.devices[id].cc += prop.minor * 0x10;
-        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB (%zu MiB free)\n",
+        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB\n",
                       id, prop.name, prop.major, prop.minor, device_vmm ? "yes" : "no",
-                      (size_t)(prop.totalGlobalMem / (1024 * 1024)), free_mem / (1024 * 1024));
+                      (size_t)(prop.totalGlobalMem / (1024 * 1024)));
 #else
         info.devices[id].smpbo = prop.sharedMemPerBlockOptin;
         info.devices[id].cc = 100*prop.major + 10*prop.minor;
-        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB (%zu MiB free)\n",
+        GGML_LOG_INFO("  Device %d: %s, compute capability %d.%d, VMM: %s, VRAM: %zu MiB\n",
                       id, prop.name, prop.major, prop.minor, device_vmm ? "yes" : "no",
-                      (size_t)(prop.totalGlobalMem / (1024 * 1024)), free_mem / (1024 * 1024));
+                      (size_t)(prop.totalGlobalMem / (1024 * 1024)));
         std::string device_name(prop.name);
         if (device_name == "NVIDIA GeForce MX450") {
             turing_devices_without_mma.push_back({ id, device_name });
@@ -306,6 +301,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
         // TODO: Check for future drivers the default scheduling strategy and
         // remove this call again when cudaDeviceScheduleSpin is default.
         if (prop.major == 12 && prop.minor == 1) {
+            CUDA_CHECK(cudaSetDevice(id));
             CUDA_CHECK(cudaSetDeviceFlags(cudaDeviceScheduleSpin));
         }