Skip to content

CUDA: fix peer access logic #3231

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 17, 2023
Merged

CUDA: fix peer access logic #3231

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 8 additions & 6 deletions ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6286,12 +6286,14 @@ void ggml_cuda_set_peer_access(const int n_tokens) {
continue;
}

int canAccessPeer;
CUDA_CHECK(cudaDeviceCanAccessPeer(&canAccessPeer, id, id_other));
if (enable_peer_access) {
CUDA_CHECK(cudaDeviceEnablePeerAccess(id_other, 0));
} else {
CUDA_CHECK(cudaDeviceDisablePeerAccess(id_other));
int can_access_peer;
CUDA_CHECK(cudaDeviceCanAccessPeer(&can_access_peer, id, id_other));
if (can_access_peer) {
if (enable_peer_access) {
CUDA_CHECK(cudaDeviceEnablePeerAccess(id_other, 0));
} else {
CUDA_CHECK(cudaDeviceDisablePeerAccess(id_other));
}
}
}
}
Expand Down