EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Refactor and optimize mooncake CI (#11162)

Browse Source 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
This commit is contained in:
Shangming Cai
2025-10-06 05:08:52 +08:00
committed by GitHub
parent 590f2da052
commit c560410da7
6 changed files with 202 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
test/srt/test_disaggregation_dp_attention.py
View File

@@ -17,21 +17,12 @@ from sglang.test.test_utils import (
class TestDisaggregationDPAttention(TestDisaggregationBase):
@classmethod
def setUpClass(cls):
super().setUpClass()
# Temporarily disable JIT DeepGEMM
cls.original_jit_deepgemm = os.environ.get("SGL_ENABLE_JIT_DEEPGEMM")
os.environ["SGL_ENABLE_JIT_DEEPGEMM"] = "false"
cls.model = DEFAULT_MODEL_NAME_FOR_TEST_MLA
parsed_url = urlparse(DEFAULT_URL_FOR_TEST)
cls.base_host = parsed_url.hostname
base_port = str(parsed_url.port)
cls.lb_port = base_port
cls.prefill_port = f"{int(base_port) + 100}"
cls.decode_port = f"{int(base_port) + 200}"
cls.prefill_url = f"http://{cls.base_host}:{cls.prefill_port}"
cls.decode_url = f"http://{cls.base_host}:{cls.decode_port}"
cls.lb_url = f"http://{cls.base_host}:{cls.lb_port}"
print(f"{cls.base_host=} {cls.lb_port=} {cls.prefill_port=} {cls.decode_port=}")
# Non blocking start servers
cls.start_prefill()