feat: reserve 20% vram when running higgs with sglang-omni

1 files changed, 8 insertions, 1 deletions

diff --git a/app/tests/test_tts_sglomni.py b/app/tests/test_tts_sglomni.py
index 58ca57c..85327e1 100644
--- a/app/tests/test_tts_sglomni.py
+++ b/app/tests/test_tts_sglomni.py
@@ -254,8 +254,15 @@ class PayloadTests(unittest.TestCase):
         payload = client._request_payload("Hello.")
         self.assertEqual(payload["max_new_tokens"], 12288)
 
-    def test_models_without_a_cap_send_no_max_new_tokens(self):
+    def test_higgs_payload_raises_the_generation_cap(self):
+        """Higgs's 2048-frame engine default caps a request at ~27 s
+        (75 fps), below a full 250-word sub-chunk."""
         client = self._make_client("higgs_audio_v3_tts")
+        payload = client._request_payload("Hello.")
+        self.assertEqual(payload["max_new_tokens"], 12288)
+
+    def test_models_without_a_cap_send_no_max_new_tokens(self):
+        client = self._make_client("moss_tts")
         self.assertNotIn("max_new_tokens",
                          client._request_payload("Hello."))