Profile-Driven Harness Implementation Log

Date: 2026-05-12

Goal

The harness should accelerate AITuner as a general tuning system, not as a collection of case-specific rules. The current implementation moves the harness toward a performance-engineering loop:

extract a compact profile from each measured trial;
rank bottleneck hypotheses from workload and probe evidence;
generate generic candidate actions from a knob-effect model;
score candidates by expected bottleneck relief, information gain, launch safety, and regression risk;
block early stop while a high-value untested candidate remains.

This is intended to apply across qwen3.5-27b chat, qwen3-235b prefill-only, qwen3-235b decode-only, and different SLOs without encoding model names, SLO constants, or known winning configs.

Code Changes

src/aituner/harness.py
- Added trial_profiles to normalize trial topology, performance, probe failures, latency quantiles, and launch failure evidence.
- Added bottleneck_hypotheses, a ranked list instead of a single active bottleneck label.
- Added candidate_actions, generated from topology and runtime knob families.
- Added experiment_plan, which selects the next high-score candidate or declares stop readiness.
- Updated harness proposal generation to prefer the profile-driven next action before falling back to legacy deterministic proposal code.
- Updated harness stop logic so convergence/validation stop is blocked when the planner still has a high-value untested candidate.
tests/test_core_flow.py
- Added coverage that a strong TP=2 incumbent with TTFT pressure still selects an unmeasured TP=4 topology candidate.
- Added coverage that decode-only TPOT pressure at max TP can prefer lowering max-num-seqs instead of blindly lowering TP.

Current Scoring Model

The candidate score is intentionally generic:

score = expected_bottleneck_relief * bottleneck_confidence
      + information_gain
      + launch_safety
      - regression_risk

Examples:

TTFT/prefill bottleneck: increasing TP and prefill batching candidates receive relief score.
Decode TPOT bottleneck: increasing TP is useful if a higher legal TP exists; if already at high TP, lowering decode concurrency can become the higher-value candidate.
Admission/queueing bottleneck: more DP or higher safe concurrency receives relief score.

The scores are not tied to qwen27b/qwen235b or a fixed TPOT/TTFT threshold. They are tied to the measured bottleneck class and legal tunable space.

Verification

Local:

python3 -m compileall -q src tests
PYTHONPATH=src python3 -m unittest tests.test_core_flow

Result: 93 tests passed.

Next Experiment

Run the same qwen3.5-27b chat 0-8k setup as the current ablation baseline:

workload: chat, input length 0-8k
SLO: TTFT p95 <= 4000ms, TPOT p95 <= 25ms, target pass rate 0.95
search: full range, inherit_incumbent_floor=false
budget: 12 total tuning iterations
LLM model: gpt-5.4
variant: harness enabled with profile-driven planner

The no-harness min-prompt baseline is already available and only needs to be reused for comparison unless the setup changes.

3.1 KiB Raw Blame History