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

80
test/srt/ep/test_eplb.py
View File

@@ -5,6 +5,7 @@ from pathlib import Path
from types import SimpleNamespace
import sglang as sgl
from sglang.srt.environ import envs
from sglang.srt.utils import kill_process_tree
from sglang.test.run_eval import run_eval
from sglang.test.test_utils import (
@@ -23,44 +24,43 @@ class _BaseTestDynamicEPLB(CustomTestCase):
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",
"--enable-eplb",
"--ep-num-redundant-experts",
"4",
"--eplb-rebalance-num-iterations",
"50",
"--expert-distribution-recorder-buffer-size",
"50",
# TODO pr-chain: enable later
# "--enable-expert-distribution-metrics",
# TODO auto determine these flags
"--expert-distribution-recorder-mode",
"stat",
"--ep-dispatch-algorithm",
"static",
*cls.extra_args,
],
env={
"SGL_ENABLE_JIT_DEEPGEMM": "0",
"SGLANG_EXPERT_LOCATION_UPDATER_CANARY": "1",
**os.environ,
},
)
with (
envs.SGLANG_ENABLE_JIT_DEEPGEMM.override(False),
envs.SGLANG_EXPERT_LOCATION_UPDATER_CANARY.override(True),
):
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",
"--enable-eplb",
"--ep-num-redundant-experts",
"4",
"--eplb-rebalance-num-iterations",
"50",
"--expert-distribution-recorder-buffer-size",
"50",
# TODO pr-chain: enable later
# "--enable-expert-distribution-metrics",
# TODO auto determine these flags
"--expert-distribution-recorder-mode",
"stat",
"--ep-dispatch-algorithm",
"static",
*cls.extra_args,
],
)
@classmethod
def tearDownClass(cls):
@@ -89,7 +89,7 @@ class TestDynamicEPLBMultiChunk(_BaseTestDynamicEPLB):
class TestStaticEPLB(CustomTestCase):
def test_save_expert_distribution_and_init_expert_location(self):
os.environ["SGL_ENABLE_JIT_DEEPGEMM"] = "0"
envs.SGLANG_ENABLE_JIT_DEEPGEMM.set(False)
with tempfile.TemporaryDirectory() as tmp_dir:
engine_kwargs = dict(
@@ -108,7 +108,7 @@ class TestStaticEPLB(CustomTestCase):
)
print(f"Action: start engine")
os.environ["SGLANG_EXPERT_DISTRIBUTION_RECORDER_DIR"] = tmp_dir
envs.SGLANG_EXPERT_DISTRIBUTION_RECORDER_DIR.set(tmp_dir)
engine = sgl.Engine(
**engine_kwargs,
disable_overlap_schedule=True,

82
test/srt/ep/test_moe_deepep.py
View File

@@ -3,6 +3,7 @@ import os
import unittest
from types import SimpleNamespace
from sglang.srt.environ import envs
from sglang.srt.utils import kill_process_tree
from sglang.test.run_eval import run_eval
from sglang.test.test_utils import (
@@ -55,48 +56,45 @@ class TestDPAttn(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",
# Test custom config
"--deepep-config",
json.dumps(
{
"normal_dispatch": {
"num_sms": 20,
"num_max_nvl_chunked_send_tokens": 16,
"num_max_nvl_chunked_recv_tokens": 256,
"num_max_rdma_chunked_send_tokens": 6,
"num_max_rdma_chunked_recv_tokens": 128,
},
"normal_combine": {
"num_sms": 20,
"num_max_nvl_chunked_send_tokens": 6,
"num_max_nvl_chunked_recv_tokens": 256,
"num_max_rdma_chunked_send_tokens": 6,
"num_max_rdma_chunked_recv_tokens": 128,
},
}
),
],
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",
# Test custom config
"--deepep-config",
json.dumps(
{
"normal_dispatch": {
"num_sms": 20,
"num_max_nvl_chunked_send_tokens": 16,
"num_max_nvl_chunked_recv_tokens": 256,
"num_max_rdma_chunked_send_tokens": 6,
"num_max_rdma_chunked_recv_tokens": 128,
},
"normal_combine": {
"num_sms": 20,
"num_max_nvl_chunked_send_tokens": 6,
"num_max_nvl_chunked_recv_tokens": 256,
"num_max_rdma_chunked_send_tokens": 6,
"num_max_rdma_chunked_recv_tokens": 128,
},
}
),
],
)
@classmethod
def tearDownClass(cls):