From 921779bb10265e4030bba3fd74e1936e58930ce1 Mon Sep 17 00:00:00 2001
From: Daniel Hiltgen <dhiltgen@users.noreply.github.com>
Date: Thu, 31 Oct 2024 13:35:31 -0700
Subject: [PATCH] Give unicode test more time to run (#7437)

* Give unicode test more time to run

Some slower GPUs (or partial CPU/GPU loads) can take more than the default 30s to complete this test

* Give more time for concurrency test

CPU inference can be very slow under stress
---
 integration/basic_test.go       | 15 ++++++++++++---
 integration/concurrency_test.go |  3 ++-
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/integration/basic_test.go b/integration/basic_test.go
index dfa921d7..88d3530e 100644
--- a/integration/basic_test.go
+++ b/integration/basic_test.go
@@ -31,7 +31,7 @@ func TestOrcaMiniBlueSky(t *testing.T) {
 }
 
 func TestUnicode(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 2*time.Minute)
+	ctx, cancel := context.WithTimeout(context.Background(), 3*time.Minute)
 	defer cancel()
 	// Set up the test data
 	req := api.GenerateRequest{
@@ -42,9 +42,15 @@ func TestUnicode(t *testing.T) {
 		Options: map[string]interface{}{
 			"temperature": 0,
 			"seed":        123,
+			// Workaround deepseek context shifting bug
+			"num_ctx":     8192,
+			"num_predict": 2048,
 		},
 	}
-	GenerateTestHelper(ctx, t, req, []string{"散射", "频率"})
+	client, _, cleanup := InitServerConnection(ctx, t)
+	defer cleanup()
+	require.NoError(t, PullIfMissing(ctx, client, req.Model))
+	DoGenerate(ctx, t, client, req, []string{"散射", "频率"}, 120*time.Second, 120*time.Second)
 }
 
 func TestExtendedUnicodeOutput(t *testing.T) {
@@ -60,7 +66,10 @@ func TestExtendedUnicodeOutput(t *testing.T) {
 			"seed":        123,
 		},
 	}
-	GenerateTestHelper(ctx, t, req, []string{"😀", "😊", "😁", "😂", "😄", "😃"})
+	client, _, cleanup := InitServerConnection(ctx, t)
+	defer cleanup()
+	require.NoError(t, PullIfMissing(ctx, client, req.Model))
+	DoGenerate(ctx, t, client, req, []string{"😀", "😊", "😁", "😂", "😄", "😃"}, 120*time.Second, 120*time.Second)
 }
 
 func TestUnicodeModelDir(t *testing.T) {
diff --git a/integration/concurrency_test.go b/integration/concurrency_test.go
index 74eb6361..165231cd 100644
--- a/integration/concurrency_test.go
+++ b/integration/concurrency_test.go
@@ -60,7 +60,8 @@ func TestMultiModelConcurrency(t *testing.T) {
 	for i := 0; i < len(req); i++ {
 		go func(i int) {
 			defer wg.Done()
-			DoGenerate(ctx, t, client, req[i], resp[i], 60*time.Second, 10*time.Second)
+			// Note: CPU based inference can crawl so don't give up too quickly
+			DoGenerate(ctx, t, client, req[i], resp[i], 90*time.Second, 30*time.Second)
 		}(i)
 	}
 	wg.Wait()