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

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

Browse Source
This commit is contained in:
Liangsheng Yin
2025-10-14 00:34:35 +08:00
committed by GitHub
parent bfadb5ea5f
commit acc2327bbd
20 changed files with 187 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
test/srt/test_two_batch_overlap.py
View File

@@ -1,9 +1,9 @@
import os
import unittest
from types import SimpleNamespace
import requests
from sglang.srt.environ import envs
from sglang.srt.model_executor.forward_batch_info import ForwardMode
from sglang.srt.two_batch_overlap import (
compute_split_seq_index,
@@ -25,26 +25,26 @@ class TestTwoBatchOverlap(unittest.TestCase):
def setUpClass(cls):
cls.model = DEFAULT_MLA_MODEL_NAME_FOR_TEST
cls.base_url = DEFAULT_URL_FOR_TEST
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=[
"--trust-remote-code",
"--tp",
"2",
"--dp",
"2",
"--enable-dp-attention",
"--moe-a2a-backend",
"deepep",
"--deepep-mode",
"normal",
"--disable-cuda-graph", # DeepEP normal does not support CUDA Graph
"--enable-two-batch-overlap",
],
env={"SGL_ENABLE_JIT_DEEPGEMM": "0", **os.environ},
)
with envs.SGLANG_ENABLE_JIT_DEEPGEMM.override(False):
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=[
"--trust-remote-code",
"--tp",
"2",
"--dp",
"2",
"--enable-dp-attention",
"--moe-a2a-backend",
"deepep",
"--deepep-mode",
"normal",
"--disable-cuda-graph", # DeepEP normal does not support CUDA Graph
"--enable-two-batch-overlap",
],
)
@classmethod
def tearDownClass(cls):
@@ -126,26 +126,26 @@ class TestQwen3TwoBatchOverlap(TestTwoBatchOverlap):
cls.model = DEFAULT_ENABLE_THINKING_MODEL_NAME_FOR_TEST
cls.base_url = DEFAULT_URL_FOR_TEST
cls.api_key = "sk-1234"
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=[
"--trust-remote-code",
"--tp",
"2",
"--dp",
"2",
"--enable-dp-attention",
"--moe-a2a-backend",
"deepep",
"--deepep-mode",
"normal",
"--disable-cuda-graph", # DeepEP normal does not support CUDA Graph
"--enable-two-batch-overlap",
],
env={"SGL_ENABLE_JIT_DEEPGEMM": "0", **os.environ},
)
with envs.SGLANG_ENABLE_JIT_DEEPGEMM.override(False):
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=[
"--trust-remote-code",
"--tp",
"2",
"--dp",
"2",
"--enable-dp-attention",
"--moe-a2a-backend",
"deepep",
"--deepep-mode",
"normal",
"--disable-cuda-graph", # DeepEP normal does not support CUDA Graph
"--enable-two-batch-overlap",
],
)
if __name__ == "__main__":