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

Make harness runtime refinement memory safe

Browse Source
This commit is contained in:
Gahow Wang
2026-05-06 17:37:31 +08:00
parent cf2e741550
commit 5d96689ea6
3 changed files with 136 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/aituner/harness.py
View File

@@ -668,8 +668,6 @@ def _runtime_refinement_proposal(
return default
tunable = set(study.engine.tunable_flags)
flag_patch: dict[str, Any] = {"tensor-parallel-size": best_tp}
if "gpu-memory-utilization" in tunable:
flag_patch["gpu-memory-utilization"] = 0.95
if "enable-chunked-prefill" in tunable:
flag_patch["enable-chunked-prefill"] = True
if "max-num-batched-tokens" not in tunable:
@@ -704,7 +702,7 @@ def _runtime_refinement_proposal(
"config_patch": {"env_patch": {}, "flag_patch": flag_patch},
"expected_effects": [
"preserve the incumbent topology",
"increase batching headroom while staying inside one runtime family",
"increase batching headroom without also raising memory pressure",
],
"incumbent_trial_id": best.get("trial_id"),
}