Files
6krrt/tests/test_local_decision_descriptions.py
adlee-was-taken 979a11b850 docs(local-decision): gate G measurement results and description tuning
Gate G results:
- Eval-set accuracy: 97.8% (PASS >= 85%)
- Held-out accuracy: 90.0% (PASS >= 90%)
- p95 latency: 502ms (PASS <= 800ms)
- 14b router resident after 100 calls: EVICTED (FAIL)

VRAM constraint: 14b router (17.76GB) + qwen3.5:4b (>=6.15GB) =
25.1GB > 24GB RTX 6000. No num_ctx allows coexistence.

STOP per plan: todos 4-17 NOT started.
2026-09-28 21:11:36 -04:00

5.0 KiB