github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-30 07:57:51 -05:00
Code Issues 11.4k Packages Projects Releases 117 Wiki Activity

Use flash attention flag for now (#4580)

Browse Source 
* put flash attention behind flag for now

* add test

* remove print

* up timeout for sheduler tests
This commit is contained in:
Jeffrey Morgan
2024-05-22 21:52:09 -07:00
committed by GitHub
parent 73630a7e85
commit 38255d2af1
4 changed files with 19 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
server/sched_test.go
View File

@@ -151,7 +151,7 @@ func newScenario(t *testing.T, ctx context.Context, modelName string, estimatedV
}
func TestRequests(t *testing.T) {
ctx, done := context.WithTimeout(context.Background(), 500*time.Millisecond)
ctx, done := context.WithTimeout(context.Background(), time.Second)
defer done()
// Same model, same request