highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 21:17:41 +01:00
Code Issues Packages Projects Releases Wiki Activity

discovery: only retry AMD GPUs (#12894)

Browse Source 
* discovery: only retry AMD GPUs

CUDA and Vulkan don't crash on unsupported devices, so retry isn't necessary.
This also refactors the code to shift the Library specific logic into the ml
package.

* review comments
This commit is contained in:
Daniel Hiltgen
2025-11-04 15:33:46 -08:00
committed by GitHub
parent 220e133fca
commit 27f1fde413
9 changed files with 96 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
discover/types.go
View File

@@ -41,7 +41,7 @@ func LogDetails(devices []ml.DeviceInfo) {
}
slog.Info("inference compute",
"id", dev.ID,
"filtered_id", dev.FilteredID,
"filter_id", dev.FilterID,
"library", dev.Library,
"compute", dev.Compute(),
"name", dev.Name,