gqa: rename long-context kernels to *_long for symmetry with *_short

Make the file + function naming symmetric:
  _gqa_decode.py        -> _gqa_decode_long.py
  _gqa_prefill.py       -> _gqa_prefill_long.py
  gqa_decode_kernel     -> gqa_decode_long_kernel
  gqa_prefill_kernel    -> gqa_prefill_long_kernel

Mirrors the existing _gqa_{decode,prefill}_short.py naming. Updates the
two imports + two call sites in milestone_gqa_headline.py and the 9
attention tests that import the kernels.

Tests: 72/72 focused regression green (tests/attention/ + Phase E + TL
discipline). milestone-gqa-headline bench passes its 7 panel/schema
assertions.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/kernbench/benches/milestone_gqa_headline.py

@@ -28,8 +28,8 @@ import json
 import os
 from pathlib import Path
 
-from kernbench.benches._gqa_decode import gqa_decode_kernel
-from kernbench.benches._gqa_prefill import gqa_prefill_kernel
+from kernbench.benches._gqa_decode_long import gqa_decode_long_kernel
+from kernbench.benches._gqa_prefill_long import gqa_prefill_long_kernel
 from kernbench.benches.registry import bench
 from kernbench.ccl.install import load_ccl_config, resolve_algorithm_config
 from kernbench.ccl.sfr_config import (
@@ -96,7 +96,7 @@ def _run_prefill_panel(ctx, *, panel: str, C: int, S_kv: int) -> None:
     o = ctx.empty((_T_Q_PREFILL * C, _D_HEAD),
                   dtype=_DTYPE, dp=dp_o, name=f"{panel}_o")
     ctx.launch(
-        panel, gqa_prefill_kernel,
+        panel, gqa_prefill_long_kernel,
         q, k, v, o,
         _T_Q_PREFILL, S_kv, _D_HEAD, C,
         _auto_dim_remap=False,
@@ -118,7 +118,7 @@ def _run_decode_panel(ctx, *, panel: str, C: int, P: int, S_kv: int) -> None:
     o = ctx.empty((_T_Q_DECODE, _H_Q_DECODE * _D_HEAD),
                   dtype=_DTYPE, dp=dp_full, name=f"{panel}_o")
     ctx.launch(
-        panel, gqa_decode_kernel,
+        panel, gqa_decode_long_kernel,
         q, k, v, o,
         _T_Q_DECODE, S_kv, _H_Q_DECODE, _H_KV_DECODE, _D_HEAD, C, P,
         _auto_dim_remap=False,