mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

CUDA: require explicit opt-in for P2P access (#21910)

Browse Source
This commit is contained in:
Johannes Gäßler
2026-04-15 16:01:46 +02:00
committed by GitHub
parent 014dca49d6
commit a6206958d2
2 changed files with 18 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/ggml-cuda.cu
+12 -10
View File
@@ -324,16 +324,18 @@ static ggml_cuda_device_info ggml_cuda_init() {
// configure logging to stdout
// CUBLAS_CHECK(cublasLoggerConfigure(1, 1, 0, nullptr));
for (int id = 0; id < info.device_count; ++id) {
ggml_cuda_set_device(id);
for (int id_other = 0; id_other < info.device_count; ++id_other) {
if (id == id_other) {
continue;
}
int can_access_peer;
CUDA_CHECK(cudaDeviceCanAccessPeer(&can_access_peer, id, id_other));
if (can_access_peer) {
CUDA_CHECK(cudaDeviceEnablePeerAccess(id_other, 0));
if (getenv("GGML_CUDA_P2P") != nullptr) {
for (int id = 0; id < info.device_count; ++id) {
ggml_cuda_set_device(id);
for (int id_other = 0; id_other < info.device_count; ++id_other) {
if (id == id_other) {
continue;
}
int can_access_peer;
CUDA_CHECK(cudaDeviceCanAccessPeer(&can_access_peer, id, id_other));
if (can_access_peer) {
CUDA_CHECK(cudaDeviceEnablePeerAccess(id_other, 0));
}
}
}
}