Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Fix context exhaustion integration test for small gpus

Daniel Hiltgen73e2c8f68fe0
diff --git a/integration/context_test.go b/integration/context_test.go
index 46fac5ead..f1342e16c 100644
--- a/integration/context_test.go
+++ b/integration/context_test.go
@@ -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)
}