root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

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

Browse Source 
* fix : cuda order of synchronization when setting a buffer

* also sync before memcpy

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Erik Scholz 2024-01-05 16:00:00 +01:00 committed by Georgi Gerganov
parent 7a9f75c38b
commit f34432ca1e
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-cuda.cu
View File

@ -10184,8 +10184,8 @@ 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) {