highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-27 00:31:41 +02:00
Code Issues Packages Projects Releases Wiki Activity

load arrays with up to 1024 elements when estimating

Browse Source 
This mirrors the old behavior before #10382
This commit is contained in:
Devon Rifkin
2025-04-27 13:45:13 -07:00
parent 6ed8898590
commit d2ee599dcf
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
server/sched.go
View File

@@ -201,7 +201,7 @@ func (s *Scheduler) processPending(ctx context.Context) {
}
// Load model for fitting
ggml, err := llm.LoadModel(pending.model.ModelPath, 0)
ggml, err := llm.LoadModel(pending.model.ModelPath, 1024)
if err != nil {
pending.errCh <- err
break