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

Prioritize uncovered prefill scheduler candidates

Browse Source
This commit is contained in:
Gahow Wang
2026-06-29 01:30:34 +08:00
parent 36c301c128
commit bfd85793f3
3 changed files with 134 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
tests/test_core_flow.py
View File

@@ -3407,6 +3407,110 @@ class CoreFlowTests(unittest.TestCase):
self.assertGreater(targets[1], targets[0])
def test_prefill_scheduler_coverage_precedes_gmu_microtune(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": 2,
"data-parallel-size": 1,
"gpu-memory-utilization": 0.7,
"max-num-seqs": 8,
},
"tunable_flags": [
"tensor-parallel-size",
"data-parallel-size",
"gpu-memory-utilization",
"max-num-batched-tokens",
"max-num-seqs",
"enable-chunked-prefill",
],
"topology_constraints": {
"allowed_tensor_parallel_sizes": [2, 4],
"allowed_data_parallel_sizes": [1],
"allowed_tp_dp_products": [2, 4],
},
},
trace_overrides={"max_concurrency": 64},
)
def write_result(name: str, request_rate: float) -> Path:
path = tmp_path / f"{name}.json"
path.write_text(
json.dumps(
{
"status": "completed",
"best_sampling_u": 0.5,
"best_request_rate": request_rate,
"best_pass_rate": 0.95,
"probes": [
{
"threshold": 0.5,
"feasible": True,
"payload": {
"request_rate": request_rate,
"pass_rate": 0.95,
"latency_summary": {
"failed_reason_counts": {"ttft_ms>4000.0": 24}
},
},
}
],
}
),
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=2,
best_request_rate=4.05,
best_request_rate_per_gpu=2.025,
trials=[
TrialSummary(
trial_id="trial-0001",
status="completed",
parallel_size=2,
best_request_rate=4.05,
best_request_rate_per_gpu=2.025,
result_path=str(write_result("trial-0001", 4.05)),
config_patch={"env_patch": {}, "flag_patch": {}},
),
TrialSummary(
trial_id="trial-0002",
status="completed",
parallel_size=4,
best_request_rate=8.0,
best_request_rate_per_gpu=2.0,
result_path=str(write_result("trial-0002", 8.0)),
config_patch={
"env_patch": {},
"flag_patch": {"tensor-parallel-size": 4},
},
),
],
)
context = build_harness_context(
study=study,
window_summary={"prompt_tokens_p95": 7774, "prompt_tail_ratio_p95_p50": 3.0},
state=state,
)
action = context["experiment_plan"]["next_action"]
self.assertEqual(action["knob_family"], "prefill-scheduler-interaction")
self.assertEqual(action["action_id"], "seed_chunked_prefill_quantum")
self.assertGreater(
action["score_factors"]["uncovered_scheduler_dimension_bonus"],
0.0,
)
def test_prefill_scheduler_not_active_for_short_prompt_workload(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
tmp_path = Path(tmp)