gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Prevent prefill convergence stop before seq probe

Browse Source
This commit is contained in:
Gahow Wang
2026-06-22 14:43:55 +08:00
parent 4607711bb5
commit fd94ab9f3b
2 changed files with 173 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

145
tests/test_core_flow.py
View File

@@ -2058,6 +2058,151 @@ class CoreFlowTests(unittest.TestCase):
{"max-num-seqs": 32},
)
def test_prefill_convergence_stop_waits_for_sequence_concurrency_probe(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
tmp_path = Path(tmp)
study_path = _write_study_assets(
tmp_path,
engine_overrides={
"base_flags": {
"host": "127.0.0.1",
"port": 8000,
"tensor-parallel-size": 4,
"data-parallel-size": 1,
"max-num-batched-tokens": 8192,
"max-num-seqs": 64,
"enable-chunked-prefill": True,
},
"tunable_flags": [
"tensor-parallel-size",
"data-parallel-size",
"max-num-batched-tokens",
"max-num-seqs",
"enable-chunked-prefill",
],
"topology_constraints": {
"allowed_tensor_parallel_sizes": [4, 8],
"allowed_data_parallel_sizes": [1, 2],
"allowed_tp_dp_products": [4, 8],
},
},
)
def write_result(name: str, best_rate: float | None, pass_rate: float) -> Path:
path = tmp_path / f"{name}.json"
payload = {
"status": "completed",
"best_sampling_u": 0.091796875 if best_rate is not None else None,
"best_request_rate": best_rate,
"best_pass_rate": pass_rate if best_rate is not None else None,
"probes": [
{
"threshold": 0.09375,
"feasible": best_rate is not None,
"payload": {
"request_rate": best_rate,
"pass_rate": pass_rate,
"early_stop_reason": (
"" if best_rate is not None else "slo_pass_rate_unrecoverable"
),
"latency_summary": {
"failed_reason_counts": {"ttft_ms>4000.0": 32}
},
},
}
],
}
path.write_text(json.dumps(payload), encoding="utf-8")
return path
study = load_study_spec(study_path)
state = StudyState(
study_id=study.study_id,
best_trial_id="trial-0001",
best_parallel_size=8,
best_sampling_u=0.091796875,
best_request_rate=2.303,
best_request_rate_per_gpu=0.288,
trials=[
TrialSummary(
trial_id="trial-0001",
status="completed",
parallel_size=8,
best_request_rate=2.303,
best_request_rate_per_gpu=0.288,
best_pass_rate=0.952,
result_path=str(write_result("trial-0001", 2.303, 0.952)),
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 8,
"data-parallel-size": 1,
},
},
),
TrialSummary(
trial_id="trial-0002",
status="completed",
parallel_size=8,
best_request_rate=2.303,
best_request_rate_per_gpu=0.288,
best_pass_rate=0.953,
result_path=str(write_result("trial-0002", 2.303, 0.953)),
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 8,
"max-num-batched-tokens": 32768,
},
},
),
TrialSummary(
trial_id="trial-0003",
status="completed",
parallel_size=8,
result_path=str(write_result("trial-0003", None, 0.0)),
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 4,
"data-parallel-size": 2,
},
},
),
TrialSummary(
trial_id="trial-0004",
status="completed",
parallel_size=8,
best_request_rate=2.303,
best_request_rate_per_gpu=0.288,
best_pass_rate=0.954,
result_path=str(write_result("trial-0004", 2.303, 0.954)),
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 8,
"data-parallel-size": 1,
"max-num-batched-tokens": 12288,
},
},
),
],
)
context = build_harness_context(
study=study,
window_summary={"prompt_tokens_p95": 24000, "prompt_tokens_p99": 32000},
state=state,
)
self.assertFalse(context["harness_stop"]["should_stop"])
self.assertEqual(
context["harness_stop"]["reason"],
"experiment_plan_has_high_value_candidate",
)
action = context["experiment_plan"]["next_action"]
self.assertEqual(action["knob_family"], "max-num-seqs")
self.assertEqual(action["config_patch"]["flag_patch"]["max-num-seqs"], 96)
self.assertEqual(action["config_patch"]["flag_patch"]["tensor-parallel-size"], 8)
def test_slo_unrecoverable_does_not_mask_latency_bottleneck(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
tmp_path = Path(tmp)