Move deep gemm related arguments to sglang.srt.environ (#11547)

test/srt/test_standalone_speculative_decoding.py

@@ -1,9 +1,9 @@
-import os
 import unittest
 from types import SimpleNamespace
 
 import requests
 
+from sglang.srt.environ import envs
 from sglang.srt.utils import kill_process_tree
 from sglang.test.few_shot_gsm8k import run_eval as run_eval_few_shot_gsm8k
 from sglang.test.test_utils import (
@@ -55,8 +55,8 @@ class TestStandaloneSpeculativeDecodingBase(CustomTestCase):
     def setUpClass(cls):
         # disable deep gemm precompile to make launch server faster
         # please don't do this if you want to make your inference workload faster
-        os.environ["SGL_JIT_DEEPGEMM_PRECOMPILE"] = "false"
-        os.environ["SGL_ENABLE_JIT_DEEPGEMM"] = "false"
+        envs.SGLANG_JIT_DEEPGEMM_PRECOMPILE.set(False)
+        envs.SGLANG_ENABLE_JIT_DEEPGEMM.set(False)
         model = cls.model
         cls.process = popen_launch_server(
             model,