ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-03 07:50:43 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

ggml : allow CUDA graphs when using pipeline parallelism (llama/13814)

Browse Source
This commit is contained in:
Diego Devesa 2025-05-27 04:05:18 -07:00 committed by Georgi Gerganov
parent cc7a0105ef
commit b75babebb2
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -1598,6 +1598,9 @@ void ggml_backend_sched_synchronize(ggml_backend_sched_t sched) {
for (int i = 0; i < sched->n_backends; i++) {
ggml_backend_synchronize(sched->backends[i]);
}
// reset the current copy to 0 so that the graphs will be similar during generation
// necessary for CUDA graphs
sched->cur_copy = 0;
}
void ggml_backend_sched_set_eval_callback(ggml_backend_sched_t sched, ggml_backend_sched_eval_callback callback, void * user_data) {