Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 01:04:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

Exchanges synchronous copy with async copy function.

Browse Source
This commit is contained in:
aendk
2025-12-16 17:21:00 +01:00
committed by Georgi Gerganov
parent 2ad0d391e1
commit 91c6026b5c
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-backend.cpp
+2 -1
View File
@@ -1498,7 +1498,8 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s
} else {
ggml_backend_synchronize_if_required(split_backend);
}
ggml_backend_tensor_copy(input, input_cpy);
ggml_backend_tensor_copy_async(input_backend, split_backend, input, input_cpy);
ggml_backend_synchronize_if_required(split_backend);
} else {
// wait for the split backend to finish using the input before overwriting it
if (sched->events[split_backend_id][sched->cur_copy] != NULL) {