gahow/agentic-pd-hybrid
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: vendor sglang v0.5.10 snapshot

Browse Source
This commit is contained in:
Gahow Wang
2026-04-24 12:29:36 +00:00
parent 78f0d15221
commit bded08301f
4308 changed files with 1200894 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
third_party/sglang/test/manual/ascend/test_ascend_deepseek_mtp.py vendored Normal file
View File

@@ -0,0 +1,94 @@
import unittest
from types import SimpleNamespace
from urllib.parse import urlparse
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 (
DEFAULT_URL_FOR_TEST,
CustomTestCase,
popen_launch_server,
)
TEST_MODEL_MATRIX = {
"/root/.cache/modelscope/hub/models/vllm-ascend/DeepSeek-R1-0528-W8A8": {
"accuracy": 0.95,
"latency": 1000,
"output_throughput": 6,
},
}
class TestAscendDeepSeekMTP(CustomTestCase):
@classmethod
def setUpClass(cls):
cls.models = TEST_MODEL_MATRIX.keys()
cls.base_url = DEFAULT_URL_FOR_TEST
cls.url = urlparse(DEFAULT_URL_FOR_TEST)
cls.common_args = [
"--trust-remote-code",
"--attention-backend",
"ascend",
"--mem-fraction-static",
0.8,
"--disable-radix-cache",
"--chunked-prefill-size",
32768,
"--tp-size",
16,
"--dp-size",
2,
"--enable-dp-attention",
"--speculative-algorithm",
"NEXTN",
"--speculative-num-steps",
1,
"--speculative-eagle-topk",
1,
"--speculative-num-draft-tokens",
2,
]
envs.SGLANG_NPU_USE_MLAPO.set(True)
envs.SGLANG_ENABLE_SPEC_V2.set(True)
envs.SGLANG_ENABLE_OVERLAP_PLAN_STREAM.set(True)
def test_a_gsm8k(self):
for model in self.models:
with self.subTest(model=model):
print(f"##=== Testing accuracy: {model} ===##")
process = popen_launch_server(
model,
self.base_url,
timeout=2400,
other_args=[
*self.common_args,
],
)
try:
args = SimpleNamespace(
num_shots=5,
data_path=None,
num_questions=1319,
max_new_tokens=512,
parallel=128,
host=f"http://{self.url.hostname}",
port=int(self.url.port),
)
metrics = run_eval_few_shot_gsm8k(args)
self.assertGreaterEqual(
metrics["accuracy"],
TEST_MODEL_MATRIX[model]["accuracy"],
)
finally:
kill_process_tree(process.pid)
if __name__ == "__main__":
unittest.main()

102
third_party/sglang/test/manual/ascend/test_ascend_w8a8_quantization.py vendored Normal file
View File

@@ -0,0 +1,102 @@
"""
Usage:
python3 -m unittest test_ascend_w8a8_quantization.TestAscendW8A8.test_gsm8k
"""
import os
import time
import unittest
from types import SimpleNamespace
from urllib.parse import urlparse
import requests
from sglang.srt.utils import kill_process_tree
from sglang.test.few_shot_gsm8k import run_eval
from sglang.test.test_utils import (
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
DEFAULT_URL_FOR_TEST,
CustomTestCase,
is_in_ci,
popen_launch_server,
)
if "ASCEND_RT_VISIBLE_DEVICES" not in os.environ:
os.environ["ASCEND_RT_VISIBLE_DEVICES"] = "0,1"
DEFAULT_PORT_FOR_SRT_TEST_RUNNER = (
7000 + int(os.environ.get("ASCEND_RT_VISIBLE_DEVICES", "0")[0]) * 100
)
DEFAULT_URL_FOR_TEST = f"http://127.0.0.1:{DEFAULT_PORT_FOR_SRT_TEST_RUNNER + 1000}"
class TestAscendW8A8(CustomTestCase):
@classmethod
def setUpClass(cls):
cls.model = "vllm-ascend/Qwen2.5-0.5B-Instruct-w8a8"
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",
"--disable-cuda-graph",
"--device",
"npu",
"--attention-backend",
"ascend",
],
)
@classmethod
def tearDownClass(cls):
kill_process_tree(cls.process.pid)
def test_gsm8k(self):
base_url = DEFAULT_URL_FOR_TEST
url = urlparse(base_url)
args = SimpleNamespace(
num_shots=5,
data_path=None,
num_questions=200,
max_new_tokens=512,
parallel=128,
host=f"http://{url.hostname}",
port=int(url.port),
)
metrics = run_eval(args)
print(metrics)
self.assertGreaterEqual(metrics["accuracy"], 0.25)
self.assertGreaterEqual(metrics["output_throughput"], 1000)
def run_decode(self, max_new_tokens):
response = requests.post(
self.base_url + "/generate",
json={
"text": "The capital of France is",
"sampling_params": {
"temperature": 0,
"max_new_tokens": max_new_tokens,
},
"ignore_eos": True,
},
)
return response.json()
def test_throughput(self):
max_tokens = 256
tic = time.perf_counter()
res = self.run_decode(max_tokens)
tok = time.perf_counter()
print(res["text"])
throughput = max_tokens / (tok - tic)
print(f"Throughput: {throughput} tokens/s")
if is_in_ci():
self.assertGreaterEqual(throughput, 25)
if __name__ == "__main__":
unittest.main()

64
third_party/sglang/test/manual/ascend/test_mindspore_models.py vendored Normal file
View File

@@ -0,0 +1,64 @@
"""
Usage:
python3 -m unittest test_mindspore_models.TestMindSporeQwen3.test_gsm8k
"""
import unittest
from types import SimpleNamespace
from sglang.srt.utils import kill_process_tree
from sglang.test.few_shot_gsm8k import run_eval
from sglang.test.test_utils import (
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
DEFAULT_URL_FOR_TEST,
CustomTestCase,
popen_launch_server,
)
class TestMindSporeQwen3(CustomTestCase):
@classmethod
def setUpClass(cls):
cls.model = "Qwen/Qwen3-8B"
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=[
"--device",
"npu",
"--model-impl",
"mindspore",
"--attention-backend",
"ascend",
"--tp-size",
"1",
"--dp-size",
"1",
"--mem-fraction-static",
0.8,
],
)
@classmethod
def tearDownClass(cls):
kill_process_tree(cls.process.pid)
def test_gsm8k(self):
args = SimpleNamespace(
num_shots=5,
data_path=None,
num_questions=200,
max_new_tokens=512,
parallel=128,
host="http://127.0.0.1",
port=int(self.base_url.split(":")[-1]),
)
metrics = run_eval(args)
print(f"{metrics=}")
self.assertGreater(metrics["accuracy"], 0.78)
if __name__ == "__main__":
unittest.main()