matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 15:57:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml: Report ordinal IDs for AMD GPUs on Windows

Browse Source 
We don't get valid UUIDs for AMD GPUs on Windows, so the best option
is to use the ordinal IDs. This brings us in line with what we currently
do on the Ollama server - the only exception is AMD GPUs on Linux, which
falls back to using ordinal IDs. The GGML implementation has no fallback
but it doesn't appear to occur for any of the GPUs that we support.

It's also possible that there are collisions between ordinal IDs for
different libraries - however the only places where we use them are
AMD on Windows and Metal on Mac, which can never occur on the same
system.
This commit is contained in:
Jesse Gross
2025-06-25 17:13:32 -07:00
committed by Jesse Gross
parent 66fb8575ce
commit 35fda7b4af
6 changed files with 45 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ml/backend.go
View File

@@ -124,9 +124,9 @@ type DeviceMemory struct {
// may not be persistent across instances of the runner.
Name string
// UUID is a unique persistent identifier for the device for matching
// with system management libraries
UUID string
// ID is an identifier for the device for matching with system
// management libraries.
ID string
// Weights is the per-layer memory needed for the model weights.
Weights []Memory
@@ -156,8 +156,8 @@ func (m DeviceMemory) LogValue() slog.Value {
attrs = append(attrs, slog.Any("Graph", m.Graph))
}
if len(attrs) > 0 && m.UUID != "" {
attrs = append([]slog.Attr{slog.String("UUID", m.UUID)}, attrs...)
if len(attrs) > 0 && m.ID != "" {
attrs = append([]slog.Attr{slog.String("ID", m.ID)}, attrs...)
}
return slog.GroupValue(attrs...)