tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Diego Devesa
2025-05-27 04:05:18 -07:00
committed by GitHub
parent 81713121ee
commit 952f3953c1
1 changed files with 3 additions and 0 deletions
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) {