nwpie/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2026-02-05 13:53:23 +02:00
Code Issues Packages Projects Releases Wiki Activity

cuda : fix compile warnings (whisper/0)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-01-30 15:56:15 +02:00
parent bbada8bfb9
commit dfd6106c84
1 changed files with 3 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -3910,14 +3910,14 @@ static void ggml_cuda_graph_evaluate_and_capture(ggml_backend_cuda_context * cud
// Launch graph
CUDA_CHECK(cudaGraphLaunch(graph->instance, cuda_ctx->stream()));
#else
GGML_UNUSED(graph_key);
graph_evaluated_or_captured = true;
#endif // USE_CUDA_GRAPH
}
}
static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx, const void * graph_key) {
#ifdef USE_CUDA_GRAPH
static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx, const void * graph_key) {
ggml_cuda_graph * graph = cuda_ctx->cuda_graph(graph_key);
if (graph->graph == nullptr) {
@@ -3930,12 +3930,8 @@ static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx, co
}
return graph->is_enabled();
#else
GGML_UNUSED(cuda_ctx);
GGML_UNUSED(graph_key);
return false;
#endif // USE_CUDA_GRAPH
}
#endif // USE_CUDA_GRAPH
static enum ggml_status ggml_backend_cuda_graph_compute(ggml_backend_t backend, ggml_cgraph * cgraph) {
ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *) backend->context;