minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

ci: prune per-commit CUDA tests — move 25 files + 13 testcases to test/manual/ (#24721)

Browse Source
This commit is contained in:
Alison Shao
2026-05-08 15:53:23 -07:00
committed by GitHub
parent aefd8e257f
commit 5fbec0e445
45 changed files with 818 additions and 525 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/manual/4-gpu-models/test_qwen35_fp4_triton.py
+77
View File
@@ -0,0 +1,77 @@
import unittest
from sglang.test.accuracy_test_runner import AccuracyTestParams
from sglang.test.ci.ci_register import register_cuda_ci
# This eval harness applies the chat_template, which is critical for qwen3.5
# to get good accuracy on gsm8k
from sglang.test.run_combined_tests import run_combined_tests
from sglang.test.test_utils import (
CustomTestCase,
ModelLaunchSettings,
)
register_cuda_ci(est_time=720, suite="stage-c-test-4-gpu-b200")
QWEN35_FP4_MODEL = "nvidia/Qwen3.5-397B-A17B-NVFP4"
ACC_THRESHOLDS = {QWEN35_FP4_MODEL: {"gsm8k": 0.95}}
class TestQwen35FP4(CustomTestCase):
def test_gsm8k(self):
base_args = [
"--tp-size",
"4",
"--chunked-prefill-size",
"2048",
"--mamba-scheduler-strategy",
"extra_buffer",
"--mamba-track-interval",
"128",
"--mamba-ssm-dtype",
"bfloat16",
"--max-running-requests",
"128",
"--reasoning-parser",
"qwen3",
"--attention-backend",
"trtllm_mha",
"--quantization",
"modelopt_fp4",
"--model-loader-extra-config",
'{"enable_multithread_load": true,"num_threads": 64}',
]
variants = [
ModelLaunchSettings(
QWEN35_FP4_MODEL,
extra_args=base_args,
variant="Triton",
),
# TODO: Fix this and re-enable it
# ModelLaunchSettings(
# QWEN35_FP4_MODEL,
# extra_args=base_args + ["--linear-attn-decode-backend", "flashinfer"],
# variant="FlashInfer",
# ),
]
run_combined_tests(
models=variants,
test_name="Qwen3.5-397B-A17B-NVFP4",
accuracy_params=AccuracyTestParams(
dataset="gsm8k",
baseline_accuracy=ACC_THRESHOLDS[QWEN35_FP4_MODEL]["gsm8k"],
num_examples=200,
num_threads=128,
max_tokens=16000,
thinking_mode="qwen3",
temperature=0.6,
top_p=0.95,
top_k=20,
),
)
if __name__ == "__main__":
unittest.main()
test/manual/4-gpu-models/test_qwen35_models_archived.py
+168
View File
@@ -0,0 +1,168 @@
"""Archived test classes split out of test/registered/4-gpu-models/test_qwen35_models.py.
Originally registered with `register_cuda_ci(...)`. Moved here as part of
the per-commit pruning effort to keep the code reachable manually.
Run with `python3 test/manual/4-gpu-models/test_qwen35_models_archived.py`.
"""
import unittest
from types import SimpleNamespace
import requests
from sglang.srt.utils import kill_process_tree
from sglang.test.accuracy_test_runner import AccuracyTestParams
from sglang.test.kits.reasoning_kit import ReasoningTokenUsageMixin
# This eval harness applies the chat_template, which is critical for qwen3.5
# to get good accuracy on gsm8k
from sglang.test.run_combined_tests import run_combined_tests
from sglang.test.run_eval import run_eval
from sglang.test.test_utils import (
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
DEFAULT_URL_FOR_TEST,
CustomTestCase,
ModelLaunchSettings,
popen_launch_server,
)
QWEN35_FP4_MODEL = "nvidia/Qwen3.5-397B-A17B-NVFP4"
ACC_THRESHOLDS = {QWEN35_FP4_MODEL: {"gsm8k": 0.95}}
class TestQwen35FP4(CustomTestCase):
def test_gsm8k(self):
base_args = [
"--tp-size",
"4",
"--chunked-prefill-size",
"2048",
"--mamba-scheduler-strategy",
"extra_buffer",
"--mamba-track-interval",
"128",
"--mamba-ssm-dtype",
"bfloat16",
"--max-running-requests",
"128",
"--reasoning-parser",
"qwen3",
"--attention-backend",
"trtllm_mha",
"--quantization",
"modelopt_fp4",
"--model-loader-extra-config",
'{"enable_multithread_load": true,"num_threads": 64}',
]
variants = [
ModelLaunchSettings(
QWEN35_FP4_MODEL,
extra_args=base_args,
variant="Triton",
),
# TODO: Fix this and re-enable it
# ModelLaunchSettings(
# QWEN35_FP4_MODEL,
# extra_args=base_args + ["--linear-attn-decode-backend", "flashinfer"],
# variant="FlashInfer",
# ),
]
run_combined_tests(
models=variants,
test_name="Qwen3.5-397B-A17B-NVFP4",
accuracy_params=AccuracyTestParams(
dataset="gsm8k",
baseline_accuracy=ACC_THRESHOLDS[QWEN35_FP4_MODEL]["gsm8k"],
num_examples=200,
num_threads=128,
max_tokens=16000,
thinking_mode="qwen3",
temperature=0.6,
top_p=0.95,
top_k=20,
),
)
class TestQwen35FP4MTP(ReasoningTokenUsageMixin, CustomTestCase):
reasoning_parser_name = "qwen3"
@classmethod
def setUpClass(cls):
cls.model = QWEN35_FP4_MODEL
cls.base_url = DEFAULT_URL_FOR_TEST
cls.init_reasoning_token_verifier()
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=[
"--tp-size",
"4",
"--chunked-prefill-size",
"2048",
"--mamba-scheduler-strategy",
"extra_buffer",
"--mamba-track-interval",
"128",
"--mamba-ssm-dtype",
"bfloat16",
"--max-running-requests",
"128",
"--reasoning-parser",
"qwen3",
"--attention-backend",
"trtllm_mha",
"--quantization",
"modelopt_fp4",
"--speculative-algorithm",
"NEXTN",
"--speculative-num-steps",
"3",
"--speculative-eagle-topk",
"1",
"--speculative-num-draft-tokens",
"4",
"--mem-fraction-static",
"0.8",
"--model-loader-extra-config",
'{"enable_multithread_load": true,"num_threads": 64}',
],
)
@classmethod
def tearDownClass(cls):
kill_process_tree(cls.process.pid)
def test_gsm8k(self):
args = SimpleNamespace(
model=self.model,
eval_name="gsm8k",
num_shots=5,
num_examples=200,
max_tokens=16000,
num_threads=128,
repeat=1,
temperature=0.6,
top_p=0.95,
top_k=20,
base_url=self.base_url,
host="http://127.0.0.1",
port=int(self.base_url.split(":")[-1]),
)
metrics = run_eval(args)
print(f"{metrics=}")
self.assertGreaterEqual(metrics["score"], ACC_THRESHOLDS[self.model]["gsm8k"])
server_info = requests.get(self.base_url + "/server_info")
avg_spec_accept_length = server_info.json()["internal_states"][0][
"avg_spec_accept_length"
]
print(f"{avg_spec_accept_length=}")
self.assertGreater(avg_spec_accept_length, 3.3)
if __name__ == "__main__":
unittest.main()
test/manual/4-gpu-models/test_qwen3_next_models.py
+34
View File
@@ -0,0 +1,34 @@
import unittest
from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.kits.eval_accuracy_kit import GSM8KMixin
from sglang.test.kits.kl_divergence_kit import KLDivergenceMixin
from sglang.test.kits.prefix_cache_branching_kit import PrefixCacheBranchingMixin
from sglang.test.server_fixtures.default_fixture import DefaultServerBase
register_cuda_ci(est_time=142, suite="stage-c-test-4-gpu-h100")
QWEN3_NEXT_MODEL = "Qwen/Qwen3-Next-80B-A3B-Instruct"
class TestQwen3Next(
GSM8KMixin, KLDivergenceMixin, PrefixCacheBranchingMixin, DefaultServerBase
):
model = QWEN3_NEXT_MODEL
cache_chunk_size = 64
gsm8k_accuracy_thres = 0.93
kl_div_thres = 0.0025
other_args = [
"--tp-size",
"4",
"--chunked-prefill-size",
"2048",
"--mamba-scheduler-strategy",
"extra_buffer",
"--mamba-track-interval",
"128",
]
if __name__ == "__main__":
unittest.main()
test/manual/4-gpu-models/test_qwen3_next_models_mtp_archived.py
+44
View File
@@ -0,0 +1,44 @@
"""Archived test classes split out of test/registered/4-gpu-models/test_qwen3_next_models_mtp.py.
Originally registered with `register_cuda_ci(...)`. Moved here as part of
the per-commit pruning effort to keep the code reachable manually.
Run with `python3 test/manual/4-gpu-models/test_qwen3_next_models_mtp_archived.py`.
"""
import unittest
from sglang.test.kits.eval_accuracy_kit import GSM8KMixin
from sglang.test.kits.kl_divergence_kit import KLDivergenceMixin
from sglang.test.server_fixtures.default_fixture import DefaultServerBase
QWEN3_NEXT_MODEL = "Qwen/Qwen3-Next-80B-A3B-Instruct"
class TestQwen3NextMTP(GSM8KMixin, KLDivergenceMixin, DefaultServerBase):
model = QWEN3_NEXT_MODEL
gsm8k_accuracy_thres = 0.93
kl_div_thres = 0.0025
other_args = [
"--trust-remote-code",
"--speculative-algorithm",
"NEXTN",
"--speculative-num-steps",
"3",
"--speculative-eagle-topk",
"1",
"--speculative-num-draft-tokens",
"4",
"--mem-fraction-static",
"0.8",
"--tp",
"4",
"--chunked-prefill-size",
"2048",
"--mamba-scheduler-strategy",
"no_buffer",
"--disable-radix-cache",
]
if __name__ == "__main__":
unittest.main()