diff --git a/test/srt/test_deepseek_v3_fp4_4gpu.py b/test/srt/test_deepseek_v3_fp4_4gpu.py index 11d3e6fd2..a63f52501 100644 --- a/test/srt/test_deepseek_v3_fp4_4gpu.py +++ b/test/srt/test_deepseek_v3_fp4_4gpu.py @@ -1,3 +1,4 @@ +import os import unittest from types import SimpleNamespace @@ -83,6 +84,7 @@ class TestDeepseekV3FP4(CustomTestCase): class TestDeepseekV3FP4MTP(CustomTestCase): @classmethod def setUpClass(cls): + os.environ["SGLANG_ENABLE_SPEC_V2"] = "1" cls.model = FULL_DEEPSEEK_V3_FP4_MODEL_PATH cls.base_url = DEFAULT_URL_FOR_TEST other_args = [ @@ -104,7 +106,6 @@ class TestDeepseekV3FP4MTP(CustomTestCase): "4", "--kv-cache-dtype", "fp8_e4m3", - "--enable-beta-spec", ] cls.process = popen_launch_server( cls.model, @@ -116,6 +117,8 @@ class TestDeepseekV3FP4MTP(CustomTestCase): @classmethod def tearDownClass(cls): kill_process_tree(cls.process.pid) + if "SGLANG_ENABLE_SPEC_V2" in os.environ: + del os.environ["SGLANG_ENABLE_SPEC_V2"] def test_a_gsm8k( self,