highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-25 17:31:22 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix context exhaustion integration test for small gpus

Browse Source 
On the smaller GPUs, the initial model load of llama2 took over 30s (the
default timeout for the DoGenerate helper)
This commit is contained in:
Daniel Hiltgen
2024-07-09 15:28:25 -07:00
parent 2d1e3c3229
commit 73e2c8f68f
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
integration/context_test.go
View File

@@ -12,7 +12,7 @@ import (
func TestContextExhaustion(t *testing.T) {
// Longer needed for small footprint GPUs
ctx, cancel := context.WithTimeout(context.Background(), 6*time.Minute)
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
defer cancel()
// Set up the test data
req := api.GenerateRequest{
@@ -25,5 +25,10 @@ func TestContextExhaustion(t *testing.T) {
"num_ctx": 128,
},
}
GenerateTestHelper(ctx, t, req, []string{"once", "upon", "lived"})
client, _, cleanup := InitServerConnection(ctx, t)
defer cleanup()
if err := PullIfMissing(ctx, client, req.Model); err != nil {
t.Fatalf("PullIfMissing failed: %v", err)
}
DoGenerate(ctx, t, client, req, []string{"once", "upon", "lived"}, 120*time.Second, 10*time.Second)
}