mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 35 Packages Projects Releases Wiki Activity

cuda : print less debug logs when disabling cuda graphs (#18868)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-01-15 20:53:01 +02:00
committed by GitHub
parent be8e3d9515
commit 6e7fc8a146
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/ggml-cuda.cu
+3 -1
View File
@@ -3730,8 +3730,10 @@ static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx) {
if (cuda_ctx->cuda_graph->graph == nullptr) {
if (ggml_cuda_info().devices[cuda_ctx->device].cc < GGML_CUDA_CC_AMPERE) {
if (!cuda_ctx->cuda_graph->disable_due_to_gpu_arch) {
GGML_LOG_DEBUG("%s: disabling CUDA graphs due to GPU architecture\n", __func__);
}
cuda_ctx->cuda_graph->disable_due_to_gpu_arch = true;
GGML_LOG_DEBUG("%s: disabling CUDA graphs due to GPU architecture\n", __func__);
}
}