furyhawk/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-21 02:05:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enable CUDA graphs on volta+turing (#25749)

Browse Source
This commit is contained in:
Alexander Heisler
2026-07-16 17:56:19 +08:00
committed by GitHub
parent 8ee54c8b32
commit 3f08ef2c51
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/ggml-cuda.cu
+1 -1
View File
@@ -3982,7 +3982,7 @@ static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx, co
ggml_cuda_graph * graph = cuda_ctx->cuda_graph(graph_key);
if (graph->graph == nullptr) {
if (ggml_cuda_info().devices[cuda_ctx->device].cc < GGML_CUDA_CC_AMPERE) {
if (ggml_cuda_info().devices[cuda_ctx->device].cc < GGML_CUDA_CC_VOLTA) {
if (!graph->disable_due_to_gpu_arch) {
GGML_LOG_DEBUG("%s: disabling CUDA graphs due to GPU architecture\n", __func__);
}