fix : cuda order of synchronization when setting a buffer (#679)

* fix : cuda order of synchronization when setting a buffer

* also sync before memcpy

---------

Co-authored-by: slaren <redacted>

diff --git a/src/ggml-cuda.cu b/src/ggml-cuda.cu
index 10c21615e6b71f57381d3559e98c29f3b0873a29..7578d21c6cf140bdae12951d1370b3d4d18557d0 100644 (file)
--- a/src/ggml-cuda.cu
+++ b/src/ggml-cuda.cu
@@ -9689,8 +9689,8 @@ static void ggml_backend_cuda_buffer_set_tensor(ggml_backend_buffer_t buffer, gg
 
     ggml_cuda_set_device(ctx->device);
     CUDA_CHECK(cudaDeviceSynchronize());
-
     CUDA_CHECK(cudaMemcpy((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice));
+    CUDA_CHECK(cudaDeviceSynchronize());
 }
 
 static void ggml_backend_cuda_buffer_get_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * tensor, void * data, size_t offset, size_t size) {