mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix vulkan PCI ID and ID handling (#12775)

Browse Source 
* Fix vulkan PCI ID and ID handling

Intel GPUs may not report PCI IDs which was leading to incorrect overlap
detection.  Switch to using the existing PCI IDs, however AMD GPUs claim not to
report PCI IDs, but actually do, so try anyway, as this is required for ADLX to
find the GPUs on Windows. Numeric IDs lead to scheduling problems, so this also
switches Vulkan to use UUID based IDs. The GPU discovery patches have been
squashed into a single patch to simplify future rebases.

* review comments
This commit is contained in:
Daniel Hiltgen
2025-10-28 15:15:35 -07:00
committed by GitHub
parent 29f63f37c8
commit 14977a9350
15 changed files with 418 additions and 447 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ml/backend/ggml/ggml.go
View File

@@ -725,7 +725,9 @@ func (b *Backend) BackendDevices() []ml.DeviceInfo {
if props.library != nil {
info.Library = C.GoString(props.library)
}
info.PCIID = fmt.Sprintf("%02x:%02x.%x", props.pci_bus_id, props.pci_device_id, props.pci_domain_id)
if props.device_id != nil {
info.PCIID = C.GoString(props.device_id)
}
info.LibraryPath = ggml.LibPaths()
if props.numeric_id != nil {
info.FilteredID = C.GoString(props.numeric_id)