highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-26 04:21:39 +02:00
Code Issues Packages Projects Releases Wiki Activity

Re-remove cuda v11 (#10694)

Browse Source 
* Re-remove cuda v11

Revert the revert - drop v11 support requiring drivers newer than Feb 23

This reverts commit c6bcdc4223.

* Simplify layout

With only one version of the GPU libraries, we can simplify things down somewhat.  (Jetsons still require special handling)

* distinct sbsa variant for linux arm64

This avoids accidentally trying to load the sbsa cuda libraries on
a jetson system which results in crashes.

* temporary prevent rocm+cuda mixed loading
This commit is contained in:
Daniel Hiltgen
2025-06-23 14:07:00 -07:00
committed by GitHub
parent 2bb69b40c7
commit 1c6669e64c
14 changed files with 67 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ml/backend/ggml/ggml/src/ggml-backend-reg.cpp vendored
View File

@@ -573,8 +573,16 @@ void ggml_backend_load_all_from_path(const char * dir_path) {
ggml_backend_load_best("blas", silent, dir_path);
ggml_backend_load_best("cann", silent, dir_path);
ggml_backend_load_best("cuda", silent, dir_path);
ggml_backend_load_best("hip", silent, dir_path);
// Avoid mixed hip+cuda configurations
const char * hip_devices = std::getenv("HIP_VISIBLE_DEVICES");
const char * rocr_devices = std::getenv("ROCR_VISIBLE_DEVICES");
if (!hip_devices && !rocr_devices) {
ggml_backend_load_best("cuda", silent, dir_path);
} else {
ggml_backend_load_best("hip", silent, dir_path);
}
ggml_backend_load_best("kompute", silent, dir_path);
ggml_backend_load_best("metal", silent, dir_path);
ggml_backend_load_best("rpc", silent, dir_path);