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

Record qwen235b harness convergence test

Browse Source
This commit is contained in:
Gahow Wang
2026-04-27 18:59:25 +08:00
parent bc884f6701
commit 71902b9fc2
3 changed files with 82 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/aituner/harness.py
View File

@@ -156,6 +156,25 @@ def _knob_harnesses(
"active_now": False,
}
)
if "expert-parallel-size" in tunable or "enable-expert-parallel" in tunable:
harnesses.append(
{
"knob_family": "expert-parallel",
"use_when": [
"Only when history or a capability profile identifies expert communication or MoE dispatch as the active bottleneck.",
],
"procedure": [
"Keep expert parallel disabled for pure TTFT/prefill tuning unless there is direct positive evidence for EP on this stack.",
"If EP is tested, change only EP-related knobs and treat launch/runtime failure as hard negative evidence.",
],
"guards": [
"Do not introduce EP as the first follow-up after a successful TP increase.",
"Do not use EP to address generic TTFT-prefill bottlenecks; TP and batching harnesses are the relevant families.",
"Do not enable EP after any launch failure involving expert-parallel knobs.",
],
"active_now": False,
}
)
if "gpu-memory-utilization" in tunable:
harnesses.append(
{
@@ -384,10 +403,10 @@ def _strong_incumbent_guard(
return default
gain = incumbent_rate / baseline_rate
latest = recent_diagnostics[-1] if recent_diagnostics else {}
if state.best_trial_id == latest.get("trial_id") and gain >= 3.0:
if state.best_trial_id == latest.get("trial_id") and gain >= 1.8:
return {
"guard_active": True,
"reason": "incumbent_exceeds_baseline_by_3x_and_latest_trial_is_best",
"reason": "incumbent_exceeds_baseline_by_1_8x_and_latest_trial_is_best",
"baseline_trial_id": baseline.get("trial_id"),
"baseline_request_rate_per_gpu": baseline_rate,
"incumbent_gain_vs_baseline": gain,
@@ -531,6 +550,7 @@ def _proposal_rules() -> list[str]:
"Pick at most one primary knob family from knob_harnesses unless the history proves a coupled change is needed.",
"Use adjacent legal values around the incumbent; avoid broad exploratory jumps.",
"When strong_incumbent.guard_active is true, do not propose runtime-only tweaks unless the relevant harness guard is positively satisfied by same-topology evidence.",
"Do not enable expert parallel for TTFT-prefill bottlenecks unless expert-parallel is the active harness and there is direct positive EP evidence.",
"If infeasible_progress blocks the last primary knob family, do not continue that family; switch families with direct bottleneck evidence or set should_stop=true.",
"If a proposed config is likely to reduce request_rate_per_gpu under the active guard, set should_stop=true instead of exploring.",
"Never repeat an already tested config signature.",