bench(milestone-gqa-headline): drop misleading single_user_/multi_user_ panels

The legacy panel names suggested batched serving semantics they never
had — all four modeled a single user with KV sharded differently
(C=1 single-cube; C=4 multi-cube Cube-SP), at toy dims (T_q=4, S_kv≤128).
The single-KV-group C=8 panel + the new milestone-gqa-decode-4cases
bench cover the meaningful comparisons; pytest regression already
covers C=1/C=4 configurations end-to-end at richer scale.

Changes:
- milestone_gqa_headline.py: drop the 4 legacy panels; _PANELS now
  contains only single_kv_group_prefill_gqa_c8_p8. Update docstring.
- tests/attention/test_milestone_gqa_headline.py: drop the 3 legacy-
  panel architectural tests (Ring-KV traffic, root-only decode write,
  per-CUBE distributed output) and test_decode_panels_use_real_gqa
  (no decode panels in this bench anymore). Equivalent properties
  are asserted in test_milestone_gqa_single_kv_group_prefill_panel.py
  (64 dma_writes, 896 ipcq_copy) and test_milestone_gqa_decode_4cases.py
  (1 dma_write at cube 6, 189 ipcq_copy).
- tests/attention/test_milestone_gqa_single_kv_group_prefill_panel.py:
  drop test_existing_prefill_panel_runner_backward_compat (it exercised
  multi_user_prefill_gqa which no longer exists).
- scripts/paper/paper_plot_gqa.py: replace the 4 legacy _LABELS entries
  with the single single_kv_group_prefill_gqa_c8_p8 label.
- Regenerate 1H_milestone_output/gqa_headline/sweep.json from the new
  panel set.

Verification: 9/9 tests pass across the 3 affected test files.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-06-15 14:50:25 -07:00
parent c164645aee
commit 65c365f858
5 changed files with 23 additions and 177 deletions
+2 -4
View File
@@ -24,10 +24,8 @@ _FIG_DIR = Path(__file__).resolve().parents[2] / "docs" / "report" / "1H-codesig
_IN_JSON = _FIG_DIR / "gqa_latency.json"
_LABELS = {
"single_user_prefill_gqa": "prefill\nC=1",
"multi_user_prefill_gqa": "prefill\nC=4 (Ring KV)",
"single_user_decode_gqa": "decode\nC=1, P=8",
"multi_user_decode_gqa": "decode\nC=4, P=8",
"single_kv_group_prefill_gqa_c8_p8":
"prefill\nC=8, P=8\n(single KV group)",
}