Update CI workflows (#1210)

python/sglang/test/runners.py

@@ -24,6 +24,7 @@ import torch.nn.functional as F
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 from sglang.srt.server import Runtime
+from sglang.test.test_utils import DEFAULT_PORT_FOR_SRT_TEST_RUNNER
 
 DEFAULT_PROMPTS = [
     # the output of gemma-2-2b from SRT is unstable on the commented prompt
@@ -171,7 +172,7 @@ class SRTRunner:
         torch_dtype,
         is_generation,
         tp_size=1,
-        port=5157,
+        port=DEFAULT_PORT_FOR_SRT_TEST_RUNNER,
     ):
         self.is_generation = is_generation
         self.runtime = Runtime(

python/sglang/test/test_utils.py

@@ -25,6 +25,7 @@ DEFAULT_MODEL_NAME_FOR_TEST = "meta-llama/Meta-Llama-3.1-8B-Instruct"
 DEFAULT_MOE_MODEL_NAME_FOR_TEST = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 
 if os.getenv("SGLANG_IS_IN_CI", "false") == "true":
+    DEFAULT_PORT_FOR_SRT_TEST_RUNNER = 5157
     DEFAULT_URL_FOR_MOE_TEST = "http://127.0.0.1:6157"
     DEFAULT_URL_FOR_ACCURACY_TEST = "http://127.0.0.1:7157"
     DEFAULT_URL_FOR_UNIT_TEST = "http://127.0.0.1:8157"