alvis 887d4b8d90 voice benchmark: rename --dry-run → --no-inference, fix log extraction ...

- --no-inference applies to all tiers (not just complex)
- metadata key: dry_run → no_inference
- extract_tier_from_logs: forward iteration (not reversed), updated regex
- GPU check skipped when --no-inference
- Fix TypeError in misclassified print when actual=None

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-03-24 07:58:05 +00:00

..

benchmark.json

Routing: 100% accuracy on realistic home assistant dataset

2026-03-24 07:53:01 +00:00

run_benchmark.py

Rename --dry-run to --no-inference, apply to all tiers in run_benchmark.py

2026-03-24 03:49:09 +00:00

run_routing_benchmark.py

routing benchmark: 1s strict deadline per query

2026-03-24 07:35:13 +00:00

run_voice_benchmark.py

voice benchmark: rename --dry-run → --no-inference, fix log extraction

2026-03-24 07:58:05 +00:00