baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Give unicode test more time to run (#7437)

Browse source 
* 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
This commit is contained in:
Daniel Hiltgen 2024-10-31 13:35:31 -07:00 committed by GitHub
parent 16f4eabe2d
commit 921779bb10
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 14 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
integration/basic_test.go
View file

@ -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) {

3
integration/concurrency_test.go
View file

@ -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()