Merge origin/main to resolve TTS ratchet conflict

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu committed 2026-08-10 15:29:25 +08:00
commit 29d2f157db
14 files changed
+261 -62

No files matched your search

@@ -43,9 +43,9 @@
],
"baseline": {
"H100": {
"throughput_qps": 0.0434,
"latency_mean": 23.0654,
"peak_memory_mb_mean": 76360.0
"throughput_qps": 0.0361,
"latency_mean": 27.6206,
"peak_memory_mb_mean": 80548.0
}
}
}
@@ -100,9 +100,9 @@
],
"baseline": {
"H100": {
"throughput_qps": 0.0606,
"latency_mean": 16.4928,
"peak_memory_mb_mean": 47164.8
"throughput_qps": 0.05263,
"latency_mean": 18.9415,
"peak_memory_mb_mean": 50053.7
}
}
},
@@ -127,9 +127,9 @@
],
"baseline": {
"H100": {
"throughput_qps": 0.0124,
"latency_mean": 80.7784,
"peak_memory_mb_mean": 55374.3429
"throughput_qps": 0.009595,
"latency_mean": 104.1058,
"peak_memory_mb_mean": 59718.0
}
}
}
+35 -1
View File
@@ -25,6 +25,7 @@ from vllm_omni.diffusion.request import OmniDiffusionRequest
from vllm_omni.diffusion.sched.interface import (
CachedRequestData,
NewRequestData,
_AdmissionWaitDecision,
)
from vllm_omni.diffusion.sched.interface import (
DiffusionSchedulerOutput as RealDiffusionSchedulerOutput,
@@ -75,6 +76,34 @@ class MockScheduler:
def num_running_requests(self) -> int:
return 0
def get_admission_wait_decision(
self,
*,
now: float,
dp_concurrent: bool = False,
) -> _AdmissionWaitDecision:
del dp_concurrent
return _AdmissionWaitDecision(
should_wait=True,
deadline=now + 0.5,
stable_window_s=0.05,
max_batch=self.max_num_running_reqs,
)
def should_end_admission_wait(
self,
decision: _AdmissionWaitDecision,
*,
now: float,
stable_since: float,
) -> bool:
waiting = self.num_waiting_requests()
return (
waiting >= decision.max_batch
or (waiting > 0 and now - stable_since >= decision.stable_window_s)
or (decision.deadline is not None and now >= decision.deadline)
)
def schedule(self) -> DiffusionSchedulerOutput:
if not self._waiting_queue:
return DiffusionSchedulerOutput(step_id=self._step_id)
@@ -536,6 +565,11 @@ class TestRequestBatchAdmission:
with pytest.raises(ValueError, match="request_batch_max_wait_ms"):
OmniDiffusionConfig(model="test", request_batch_max_wait_ms=-1.0)
@pytest.mark.parametrize("bad_wait", [float("nan"), float("inf"), float("-inf")])
def test_config_rejects_nonfinite_request_batch_max_wait_ms(self, bad_wait: float) -> None:
with pytest.raises(ValueError, match="request_batch_max_wait_ms"):
OmniDiffusionConfig(model="test", request_batch_max_wait_ms=bad_wait)
def test_config_normalizes_request_batch_max_wait_ms_to_float(self) -> None:
config = OmniDiffusionConfig(model="test", request_batch_max_wait_ms=5)
@@ -603,7 +637,7 @@ class TestRequestBatchAdmission:
start = time.monotonic()
with engine._cv:
engine._wait_for_request_batch_admission_locked()
engine._wait_for_admission_if_needed_locked()
waited_s = time.monotonic() - start
# Stable-window exit (~50ms), not the full 1000ms deadline.
@@ -146,7 +146,7 @@ def _make_engine_with_loop(
engine.executor = _ConcurrencyTrackingExecutor(rpc_delay=rpc_delay)
sched = RequestScheduler()
sched.initialize(SimpleNamespace(max_num_seqs=1))
sched.initialize(SimpleNamespace(max_num_seqs=1, request_batch_max_wait_ms=0.0))
engine.scheduler = sched
engine.step_execution = False
engine.supports_request_batch = False
+88 -1
View File
@@ -244,7 +244,86 @@ class TestGetRequestBatchSamplingParamsKey:
class TestRequestScheduler:
def setup_method(self) -> None:
self.scheduler: RequestScheduler = RequestScheduler()
self.scheduler.initialize(SimpleNamespace())
self.scheduler.initialize(SimpleNamespace(request_batch_max_wait_ms=0.0))
def test_admission_wait_disabled_with_zero_max_wait(self) -> None:
self.scheduler.initialize(SimpleNamespace(request_batch_max_wait_ms=0.0))
decision = self.scheduler.get_admission_wait_decision(now=10.0)
assert decision.should_wait is False
@pytest.mark.parametrize(
("dp_concurrent", "expected_stable_window_s"),
[(False, 0.05), (True, 0.3)],
)
def test_admission_wait_decision_encodes_coalescing_policy(
self,
dp_concurrent: bool,
expected_stable_window_s: float,
) -> None:
self.scheduler.initialize(
SimpleNamespace(
max_num_seqs=4,
request_batch_max_wait_ms=1000.0,
)
)
decision = self.scheduler.get_admission_wait_decision(
now=10.0,
dp_concurrent=dp_concurrent,
)
assert decision.should_wait is True
assert decision.deadline == 11.0
assert decision.stable_window_s == expected_stable_window_s
assert decision.max_batch == 4
def test_admission_wait_disabled_while_wave_is_running(self) -> None:
self.scheduler.initialize(
SimpleNamespace(
max_num_seqs=1,
request_batch_max_wait_ms=1000.0,
)
)
self.scheduler.add_request(_make_request("running"))
self.scheduler.schedule()
decision = self.scheduler.get_admission_wait_decision(now=10.0)
assert decision.should_wait is False
def test_admission_wait_end_conditions(self) -> None:
self.scheduler.initialize(
SimpleNamespace(
max_num_seqs=2,
request_batch_max_wait_ms=1000.0,
)
)
decision = self.scheduler.get_admission_wait_decision(now=10.0)
self.scheduler.add_request(_make_request("a"))
assert not self.scheduler.should_end_admission_wait(
decision,
now=10.01,
stable_since=10.0,
)
assert self.scheduler.should_end_admission_wait(
decision,
now=10.05,
stable_since=10.0,
)
assert self.scheduler.should_end_admission_wait(
decision,
now=11.0,
stable_since=11.0,
)
self.scheduler.add_request(_make_request("b"))
assert self.scheduler.should_end_admission_wait(
decision,
now=10.01,
stable_since=10.01,
)
def test_single_request_success_lifecycle(self) -> None:
req_id = self.scheduler.add_request(_make_request("a"))
@@ -898,6 +977,14 @@ class TestStepScheduler:
self.scheduler: StepScheduler = StepScheduler()
self.scheduler.initialize(SimpleNamespace())
def test_admission_wait_is_not_supported(self) -> None:
decision = self.scheduler.get_admission_wait_decision(
now=10.0,
dp_concurrent=True,
)
assert decision.should_wait is False
def test_single_request_step_lifecycle(self) -> None:
request = _make_step_request("step", num_inference_steps=3)
req_id = self.scheduler.add_request(request)
@@ -389,6 +389,24 @@ def test_serve_cli_accepts_request_batch_max_wait_ms():
assert stage_cfg["engine_args"]["request_batch_max_wait_ms"] == 250.0
@pytest.mark.parametrize("bad_wait", ["nan", "inf", "-inf", "-1"])
def test_serve_cli_rejects_invalid_request_batch_max_wait_ms(bad_wait: str):
parser = TrackingArgumentParser()
subparsers = parser.add_subparsers(dest="command")
OmniServeCommand().subparser_init(subparsers)
with pytest.raises(SystemExit):
parser.parse_args(
[
"serve",
"Qwen/Qwen-Image",
"--omni",
"--request-batch-max-wait-ms",
bad_wait,
]
)
def test_serve_cli_accepts_additional_config():
"""Ensure diffusion serve CLI exposes additional_config and forwards it to stage config."""
parser = TrackingArgumentParser()