CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update ggml/src/ggml-sycl/ggml-sycl.cpp

Browse Source
This commit is contained in:
Neo Zhang Jianyu
2025-04-08 13:16:14 +08:00
committed by GitHub
parent d271172ab1
commit 76f2ed3d77
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-sycl/ggml-sycl.cpp
View File

@@ -372,7 +372,8 @@ static void ggml_backend_sycl_buffer_set_tensor(ggml_backend_buffer_t buffer,
auto stream = &(dpct::dev_mgr::instance().get_device(ctx->device).default_queue()); auto stream = &(dpct::dev_mgr::instance().get_device(ctx->device).default_queue());
SYCL_CHECK( SYCL_CHECK(
CHECK_TRY_ERROR(dpct::dev_mgr::instance().get_device(ctx->device).queues_wait_and_throw())); CHECK_TRY_ERROR(dpct::dev_mgr::instance().get_device(ctx->device).queues_wait_and_throw()));
//note: use host buffer to save the data from mmap(), then copy to device. It's workaround for mmap() issue on PVC GPU. // Note: Use host buffer to save the data from mmap(), then copy to device. It's workaround for mmap() issue on PVC GPU.
// This function will be called during load model from disk. Use memory buffer replace dynamic won't save more time and brings potential memory leak risk here.
char* host_buf = (char*)malloc(size); char* host_buf = (char*)malloc(size);
memcpy(host_buf, data, size); memcpy(host_buf, data, size);
SYCL_CHECK( SYCL_CHECK(