chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

Multiple refactors of DeepSeek V32 and context parallel (#16305)

Browse Source
This commit is contained in:
Baizhou Zhang
2026-01-03 02:21:22 +08:00
committed by GitHub
parent 1cfd2b2ded
commit f07e76b229
7 changed files with 193 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
test/srt/run_suite.py
View File

@@ -133,8 +133,9 @@ suites = {
TestFile("test_deepseek_v3_mtp.py", 275),
TestFile("test_disaggregation_hybrid_attention.py", 600),
TestFile("models/test_kimi_k2_models.py", 200),
TestFile("test_deepseek_v32_basic.py", 275),
TestFile("test_deepseek_v32_mtp.py", 275),
TestFile("test_deepseek_v32_basic.py", 360),
TestFile("test_deepseek_v32_mtp.py", 360),
TestFile("test_deepseek_v32_cp_single_node.py", 360),
TestFile("models/test_mimo_models.py", 200),
],
"per-commit-8-gpu-h20": [

57
test/srt/test_deepseek_v32_basic.py
View File

@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
DEEPSEEK_V32_MODEL_PATH = "deepseek-ai/DeepSeek-V3.2-Exp"
class TestDeepseekV32Basic(CustomTestCase):
class TestDeepseekV32DP(CustomTestCase):
@classmethod
def setUpClass(cls):
cls.model = DEEPSEEK_V32_MODEL_PATH
@@ -74,5 +74,60 @@ class TestDeepseekV32Basic(CustomTestCase):
self.assertGreater(speed, 50)
class TestDeepseekV32TP(CustomTestCase):
@classmethod
def setUpClass(cls):
cls.model = DEEPSEEK_V32_MODEL_PATH
cls.base_url = DEFAULT_URL_FOR_TEST
other_args = [
"--trust-remote-code",
"--tp",
"8",
]
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=other_args,
)
@classmethod
def tearDownClass(cls):
kill_process_tree(cls.process.pid)
def test_a_gsm8k(
self,
): # Append an "a" to make this test run first (alphabetically) to warm up the server
args = SimpleNamespace(
num_shots=20,
data_path=None,
num_questions=1400,
parallel=1400,
max_new_tokens=512,
host="http://127.0.0.1",
port=int(self.base_url.split(":")[-1]),
)
metrics = run_eval_few_shot_gsm8k(args)
print(f"{metrics=}")
if is_in_ci():
write_github_step_summary(
f"### test_gsm8k (deepseek-v32)\n" f'{metrics["accuracy"]=:.3f}\n'
)
self.assertGreater(metrics["accuracy"], 0.935)
def test_bs_1_speed(self):
args = BenchArgs(port=int(self.base_url.split(":")[-1]), max_new_tokens=2048)
acc_length, speed = send_one_prompt(args)
print(f"{speed=:.2f}")
if is_in_ci():
write_github_step_summary(
f"### test_bs_1_speed (deepseek-v32)\n" f"{speed=:.2f} token/s\n"
)
self.assertGreater(speed, 70)
if __name__ == "__main__":
unittest.main()

5
test/manual/test_deepseek_v32_cp_single_node.py → test/srt/test_deepseek_v32_cp_single_node.py
View File

@@ -50,6 +50,8 @@ class TestDeepseekV32CP(CustomTestCase):
"--max-running-requests",
"32",
"--enable-nsa-prefill-context-parallel",
"--nsa-prefill-cp-mode",
"in-seq-split",
]
cls.process = popen_launch_server(
cls.model,
@@ -104,9 +106,6 @@ class TestDeepseekV32CPMode1(CustomTestCase):
"--trust-remote-code",
"--tp",
"8",
"--dp",
"1",
"--enable-dp-attention",
"--speculative-algorithm",
"EAGLE",
"--speculative-num-steps",

82
test/srt/test_deepseek_v32_mtp.py
View File

@@ -18,7 +18,7 @@ from sglang.test.test_utils import (
FULL_DEEPSEEK_V32_MODEL_PATH = "deepseek-ai/DeepSeek-V3.2-Exp"
class TestDeepseekV32MTP(CustomTestCase):
class TestDeepseekV32DPMTP(CustomTestCase):
@classmethod
def setUpClass(cls):
cls.model = FULL_DEEPSEEK_V32_MODEL_PATH
@@ -101,5 +101,85 @@ class TestDeepseekV32MTP(CustomTestCase):
self.assertGreater(speed, 75)
class TestDeepseekV32TPMTP(CustomTestCase):
@classmethod
def setUpClass(cls):
cls.model = FULL_DEEPSEEK_V32_MODEL_PATH
cls.base_url = DEFAULT_URL_FOR_TEST
other_args = [
"--trust-remote-code",
"--tp",
"8",
"--speculative-algorithm",
"EAGLE",
"--speculative-num-steps",
"3",
"--speculative-eagle-topk",
"1",
"--speculative-num-draft-tokens",
"4",
"--mem-frac",
"0.7",
]
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=other_args,
)
@classmethod
def tearDownClass(cls):
kill_process_tree(cls.process.pid)
def test_a_gsm8k(
self,
): # Append an "a" to make this test run first (alphabetically) to warm up the server
requests.get(self.base_url + "/flush_cache")
args = SimpleNamespace(
num_shots=20,
data_path=None,
num_questions=1400,
parallel=1400,
max_new_tokens=512,
host="http://127.0.0.1",
port=int(self.base_url.split(":")[-1]),
)
metrics = run_eval_few_shot_gsm8k(args)
print(f"{metrics=}")
server_info = requests.get(self.base_url + "/get_server_info")
avg_spec_accept_length = server_info.json()["internal_states"][0][
"avg_spec_accept_length"
]
print(f"{avg_spec_accept_length=}")
if is_in_ci():
write_github_step_summary(
f"### test_gsm8k (deepseek-v32 mtp)\n"
f'{metrics["accuracy"]=:.3f}\n'
f"{avg_spec_accept_length=:.2f}\n"
)
self.assertGreater(metrics["accuracy"], 0.94)
self.assertGreater(avg_spec_accept_length, 2.7)
def test_bs_1_speed(self):
args = BenchArgs(port=int(self.base_url.split(":")[-1]), max_new_tokens=2048)
acc_length, speed = send_one_prompt(args)
print(f"{acc_length=:.2f} {speed=:.2f}")
if is_in_ci():
write_github_step_summary(
f"### test_bs_1_speed (deepseek-v32 mtp)\n"
f"{acc_length=:.2f}\n"
f"{speed=:.2f} token/s\n"
)
self.assertGreater(acc_length, 2.7)
self.assertGreater(speed, 130)
if __name__ == "__main__":
unittest.main()