Fix mem fraction static for nightly tests (#11076)

test/srt/test_multi_instance_release_memory_occupation.py

@@ -216,7 +216,7 @@ def _run_sglang_subprocess(
         del hf_model
         hf_model = None
         torch.cuda.empty_cache()
-        time.sleep(5)
+        time.sleep(3)
         torch.cuda.empty_cache()
         _curr_usage = get_gpu_memory_gb(rank)
         assert (

test/srt/test_nightly_text_models_gsm8k_eval.py

@@ -63,10 +63,15 @@ class TestNightlyGsm8KEval(unittest.TestCase):
             for model in model_group:
                 model_count += 1
                 with self.subTest(model=model):
+                    other_args = ["--tp", "2"] if is_tp2 else []
+
+                    if model == "meta-llama/Llama-3.1-70B-Instruct":
+                        other_args.extend(["--mem-fraction-static", "0.9"])
+
                     process = popen_launch_server(
                         model=model,
+                        other_args=other_args,
                         base_url=self.base_url,
-                        other_args=["--tp", "2"] if is_tp2 else [],
                         timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
                     )