cuda : clear error after changing peer access (llama/10153)

diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu
index b57f1b3b794694d6102cd322a235e1a5177a782f..e68e405501bedda0eb35c527b66f4103f8d99b14 100644 (file)
--- a/ggml/src/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda.cu
@@ -1297,11 +1297,17 @@ static void ggml_cuda_set_peer_access(const int n_tokens, int main_device) {
                     cudaError_t err = cudaDeviceEnablePeerAccess(id_other, 0);
                     if (err != cudaErrorPeerAccessAlreadyEnabled) {
                         CUDA_CHECK(err);
+                    } else {
+                        // reset the error
+                        cudaGetLastError();
                     }
                 } else {
                     cudaError_t err = cudaDeviceDisablePeerAccess(id_other);
                     if (err != cudaErrorPeerAccessNotEnabled) {
                         CUDA_CHECK(err);
+                    } else {
+                        // reset the error
+                        cudaGetLastError();
                     }
                 }
             }