Skip to content

LLM inference in C/C++

C++ ggml

Enable CUDA graphs on volta+turing (#25749)

Alexander Heisler3f08ef2c5197
diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index d644436e50..87adc3ab74 100644
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -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__);
}