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>

tests/attention/test_gqa_long_context.py

@@ -23,8 +23,8 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from kernbench.benches._gqa_decode import gqa_decode_kernel  # noqa: F401
-from kernbench.benches._gqa_prefill import gqa_prefill_kernel  # noqa: F401
+from kernbench.benches._gqa_decode_long import gqa_decode_long_kernel  # noqa: F401
+from kernbench.benches._gqa_prefill_long import gqa_prefill_long_kernel  # noqa: F401
 from kernbench.ccl.install import load_ccl_config, resolve_algorithm_config
 from kernbench.ccl.sfr_config import (
     configure_sfr_intercube_multisip,
@@ -84,7 +84,7 @@ def test_decode_long_context_32k_completes():
                       dtype=DTYPE, dp=dp_full, name="q_long_dec_2")
         ctx.launch(
             "gqa_decode_long_32k",
-            gqa_decode_kernel,
+            gqa_decode_long_kernel,
             q, k, v, o,
             1, S_kv, 8, 1, D_HEAD,
             1, P,
@@ -141,7 +141,7 @@ def test_prefill_long_context_completes_after_scope_discipline():
                       dtype=DTYPE, dp=dp_o, name="o_long_pre")
         ctx.launch(
             "gqa_prefill_long_64k",
-            gqa_prefill_kernel,
+            gqa_prefill_long_kernel,
             q, k, v, o,
             T_q, S_kv, D_HEAD, C,
             _auto_dim_remap=False,