Harness: explore gpu-memory-utilization (and raise max-num-seqs) before Stop-B

The harness defined a gpu-memory-utilization family but hard-coded active_now=False
and never generated a candidate for it, and only ever *lowered* max-num-seqs for
decode_tpot. So on the decode-bound 27B incumbent it stopped at TP4=0.648 while the
naive (use_harness=false) baseline freely found gpu-memory-utilization=0.94 -> 0.873
(+35%) and max-num-seqs=48. That made the harness look worse than naive -- a real
coverage gap, not bad luck.

Fix in _runtime_candidate_actions (topology-before-runtime gated: only once topology
has moved off the baseline, so a baseline latency bottleneck still gets a TP change):
- Add a gpu-memory-utilization hill-climb candidate (+0.02/step toward a 0.97 safe
  ceiling) for decode_tpot/admission incumbents, scored high enough (>=0.35) to block
  a premature Stop-B until it is tried; the incumbent guard keeps the step only if
  per-GPU rate improves and the engine launches, and the tested signature terminates
  the climb (so 0.96 OOM/regression backs off to 0.94 automatically).
- Let max-num-seqs *rise* for decode_tpot (not only fall) to exploit decode parallelism.
- Activate the gpu-memory-utilization harness family for decode_tpot/admission.

Verified: new unit test asserts a settled TP4 decode-bound incumbent gets a
gpu-memory-utilization raise (0.9->0.92) and no stop while untried. 115 tests pass.
Empirical reliability (harness recovers ~0.87 and stops) to be confirmed by re-run.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-06-19 10:25:47 +08:00
parent 95c02d7dd9
commit a3523f5601
2 changed files with 182 additions and 3 deletions

View File

@@ -1318,6 +1318,113 @@ class CoreFlowTests(unittest.TestCase):
},
)
def test_harness_raises_gpu_mem_util_on_settled_decode_bound_incumbent(self) -> None:
"""Regression for the coverage gap that let the naive baseline beat the harness:
a settled TP incumbent that is decode_tpot-bound must get a gpu-memory-utilization
raise (KV-cache headroom) before the harness is allowed to stop."""
with tempfile.TemporaryDirectory() as tmp:
tmp_path = Path(tmp)
study_path = _write_study_assets(
tmp_path,
slo_overrides={
"ttft_rule": {"kind": "fixed_ms", "threshold_ms": 4000},
"tpot_rule": {"kind": "fixed_ms", "threshold_ms": 50},
},
engine_overrides={
"tunable_flags": [
"tensor-parallel-size",
"gpu-memory-utilization",
],
"topology_constraints": {
"allowed_tensor_parallel_sizes": [1, 2, 4],
"allowed_data_parallel_sizes": [1],
"allowed_tp_dp_products": [1, 2, 4],
},
},
)
study = load_study_spec(study_path)
result_path = tmp_path / "trial-0002.json"
result_path.write_text(
json.dumps(
{
"status": "completed",
"best_sampling_u": 0.074,
"best_request_rate": 2.6,
"best_pass_rate": 0.97,
"probes": [
{
"threshold": 0.074,
"feasible": True,
"payload": {
"request_count": 300,
"pass_rate": 0.97,
"request_rate": 2.6,
"latency_summary": {"failed_reason_counts": {}},
},
},
{
"threshold": 0.09,
"feasible": False,
"payload": {
"request_count": 300,
"pass_rate": 0.6,
"request_rate": 3.2,
"early_stop_reason": "slo_pass_rate_unrecoverable",
"latency_summary": {
"failed_reason_counts": {"tpot_ms>50.0": 90}
},
},
},
],
}
),
encoding="utf-8",
)
state = StudyState(
study_id=study.study_id,
best_trial_id="trial-0002",
best_request_rate=2.6,
best_request_rate_per_gpu=0.65,
trials=[
TrialSummary(
trial_id="trial-0001",
status="completed",
best_request_rate=1.1,
best_request_rate_per_gpu=0.275,
config_patch={"env_patch": {}, "flag_patch": {"tensor-parallel-size": 2}},
),
TrialSummary(
trial_id="trial-0002",
status="completed",
best_request_rate=2.6,
best_request_rate_per_gpu=0.65,
result_path=str(result_path),
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 4,
"gpu-memory-utilization": 0.9,
},
},
),
],
)
context = build_harness_context(
study=study, window_summary={"prompt_tokens_p95": 1500}, state=state
)
proposal = build_harness_guided_proposal(context)
self.assertIsNotNone(proposal)
self.assertFalse(proposal.should_stop)
# TP4 preserved; gpu-memory-utilization hill-climbed one step (0.9 -> 0.92).
self.assertEqual(
proposal.config_patch.flag_patch.get("tensor-parallel-size"), 4
)
self.assertEqual(
proposal.config_patch.flag_patch.get("gpu-memory-utilization"), 0.92
)
# And the harness must NOT authorize a stop while that knob is untried.
self.assertIsNone(build_harness_stop_proposal(context))
def test_harness_validates_unmeasured_tp_frontier_before_runtime_refinement(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
tmp_path = Path(tmp)