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>

src/kernbench/benches/1H_milestone_output/gqa_headline/sweep.json

@@ -1,11 +1,7 @@
 {
   "version": 1,
   "panels": [
-    "single_user_prefill_gqa",
-    "multi_user_prefill_gqa",
-    "single_kv_group_prefill_gqa_c8_p8",
-    "single_user_decode_gqa",
-    "multi_user_decode_gqa"
+    "single_kv_group_prefill_gqa_c8_p8"
   ],
   "config": {
     "T_q_prefill": 4,
@@ -16,30 +12,6 @@
     "d_head": 64
   },
   "rows": [
-    {
-      "panel": "single_user_prefill_gqa",
-      "kind": "prefill",
-      "C": 1,
-      "S_kv": 16,
-      "op_log_summary": {
-        "gemm_count": 2,
-        "ipcq_copy_count": 0,
-        "dma_read_count": 3,
-        "dma_write_count": 1
-      }
-    },
-    {
-      "panel": "multi_user_prefill_gqa",
-      "kind": "prefill",
-      "C": 4,
-      "S_kv": 16,
-      "op_log_summary": {
-        "gemm_count": 32,
-        "ipcq_copy_count": 24,
-        "dma_read_count": 12,
-        "dma_write_count": 4
-      }
-    },
     {
       "panel": "single_kv_group_prefill_gqa_c8_p8",
       "kind": "prefill",
@@ -54,32 +26,6 @@
         "dma_read_count": 192,
         "dma_write_count": 64
       }
-    },
-    {
-      "panel": "single_user_decode_gqa",
-      "kind": "decode",
-      "C": 1,
-      "P": 8,
-      "S_kv": 64,
-      "op_log_summary": {
-        "gemm_count": 16,
-        "ipcq_copy_count": 21,
-        "dma_read_count": 24,
-        "dma_write_count": 1
-      }
-    },
-    {
-      "panel": "multi_user_decode_gqa",
-      "kind": "decode",
-      "C": 4,
-      "P": 8,
-      "S_kv": 128,
-      "op_log_summary": {
-        "gemm_count": 64,
-        "ipcq_copy_count": 93,
-        "dma_read_count": 96,
-        "dma_write_count": 1
-      }
     }
   ]
 }

src/kernbench/benches/milestone_gqa_headline.py

@@ -14,18 +14,16 @@ Restrictions:
   - No figure renderers (defer to a separate cycle)
 
 Panels:
-  single_user_prefill_gqa         : prefill C=1, T_q=4, S_kv=16
-  multi_user_prefill_gqa          : prefill C=4 Ring KV, T_q=4, S_kv=16
   single_kv_group_prefill_gqa_c8_p8: prefill C=8 snake Ring KV +
                                      intra-CUBE PE-SP (all 64 ranks),
                                      T_q=S_kv=1K, d_head=128 — the
                                      LLaMA-3.1-70B single-KV-group target
                                      (scratch-limited; 32K headline awaits
                                      Q-axis kernel tiling)
-  single_user_decode_gqa          : decode C=1, P=8, h_q=8, h_kv=1, S_kv=64
-                                    (M-fold + intra-cube row-then-col chain)
-  multi_user_decode_gqa           : decode C=4, P=8, h_q=8, h_kv=1, S_kv=128
-                                    (M-fold + 2-level chain reduce-to-root)
+
+Decode panels live in ``milestone_gqa_decode_4cases.py`` (the 4-cases
+comparative study). Legacy C=1 / C=4 panels were dropped — pytest
+regression already covers those configurations.
 
 Gated by ``GQA_HEADLINE_RUN=1``.
 """
@@ -59,17 +57,11 @@ _H_Q_DECODE = 8        # real GQA: G = H_Q_DECODE / H_KV_DECODE = 8
 _H_KV_DECODE = 1
 
 _PANELS = (
-    "single_user_prefill_gqa",
-    "multi_user_prefill_gqa",
     "single_kv_group_prefill_gqa_c8_p8",
-    "single_user_decode_gqa",
-    "multi_user_decode_gqa",
 )
 
 # Each entry: (kind, panel-specific params)
 _PANEL_DISPATCH: dict[str, tuple[str, dict]] = {
-    "single_user_prefill_gqa": ("prefill", {"C": 1, "S_kv": _S_KV_PREFILL}),
-    "multi_user_prefill_gqa":  ("prefill", {"C": 4, "S_kv": _S_KV_PREFILL}),
     "single_kv_group_prefill_gqa_c8_p8": ("prefill", {
         "C": 8, "P": 8,
         # T_q = S_kv = 1024 (one-shot long-context prefill, scratch-limited).
@@ -82,8 +74,6 @@ _PANEL_DISPATCH: dict[str, tuple[str, dict]] = {
         "T_q": 1_024, "S_kv": 1_024,
         "d_head": 128,
     }),
-    "single_user_decode_gqa":  ("decode",  {"C": 1, "P": 8, "S_kv": 64}),
-    "multi_user_decode_gqa":   ("decode",  {"C": 4, "P": 8, "S_kv": 128}),
 }