highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-06-30 21:50:56 +02:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Devon Rifkin
2025-04-29 10:21:36 -07:00
committed by GitHub
parent 6ec71d8fb6 fe5b9bb21b
commit db428adbb8
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

@ -58,7 +58,7 @@ var defaultModelsPerGPU = 3
// Default automatic value for parallel setting // Default automatic value for parallel setting
// Model will still need to fit in VRAM. If this setting won't fit // 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 // 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") var ErrMaxQueue = errors.New("server busy, please try again. maximum pending requests exceeded")