We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 67630cf commit f056852Copy full SHA for f056852
ggml/src/ggml-cuda/mean.cu
@@ -40,7 +40,7 @@ void ggml_cuda_op_mean(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
40
ctx.cuda_graph->disable_due_to_gpu_arch || ctx.cuda_graph->disable_due_to_too_many_updates ||
41
ctx.cuda_graph->disable_due_to_failed_graph_capture))) {
42
#else
43
- (ncols > 65536)) {
+ (ncols > 65536) && (iscapturing == cudaStreamCaptureStatusNone)) {
44
#endif // USE_CUDA_GRAPH
45
// Single row - use device-wide reduction
46
size_t tmp_size = 0;
0 commit comments