Merge pull request #10468 from ollama/drifkin/num-parallel-1

db428adb · Devon Rifkin · GitHub · 6ec71d8f · fe5b9bb2 · db428adb
Unverified Commit db428adb authored Apr 29, 2025 by Devon Rifkin Committed by GitHub Apr 29, 2025
Show whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

server/sched.go server/sched.go +1 -1

No files found.
--- a/server/sched.go
+++ b/server/sched.go
@@ -58,7 +58,7 @@ var defaultModelsPerGPU = 3
 // Default automatic value for parallel setting
 // Model will still need to fit in VRAM.  If this setting won't fit
 // we'll back off down to 1 to try to get it to fit
-var defaultParallel = 4
+var defaultParallel = 2

 var ErrMaxQueue = errors.New("server busy, please try again.  maximum pending requests exceeded")