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/_gqa_decode_long.py

@@ -67,7 +67,7 @@ def _merge_running(m_local, l_local, O_local, m_other, l_other, O_other, *, tl):
     return m_new, l_new, O_new
 
 
-def gqa_decode_kernel(
+def gqa_decode_long_kernel(
     q_ptr: int,
     k_ptr: int,
     v_ptr: int,

src/kernbench/benches/_gqa_prefill_long.py

@@ -25,7 +25,7 @@ Deviations from ADR-0060 §5.5 — deferred to later phases:
 from __future__ import annotations
 
 
-def gqa_prefill_kernel(
+def gqa_prefill_long_kernel(
     q_ptr: int,
     k_ptr: int,
     v_ptr: int,

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_decode_long import gqa_decode_long_kernel
-from kernbench.benches._gqa_prefill import gqa_prefill_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,

tests/attention/test_gqa_decode.py

@@ -23,7 +23,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from kernbench.benches._gqa_decode import gqa_decode_kernel  # noqa: F401  (Phase 2 deliverable)
+from kernbench.benches._gqa_decode_long import gqa_decode_long_kernel  # noqa: F401  (Phase 2 deliverable)
 from kernbench.policy.placement.dp import DPPolicy
 from kernbench.runtime_api.bench_runner import run_bench
 from kernbench.runtime_api.types import resolve_device
@@ -72,7 +72,7 @@ def _run_decode_p1(*, h_q: int, h_kv: int):
                       dtype=DTYPE, dp=dp, name=f"o_h{h_q}_kv{h_kv}")
         ctx.launch(
             f"gqa_decode_p1_h{h_q}_kv{h_kv}",
-            gqa_decode_kernel,
+            gqa_decode_long_kernel,
             q, k, v, o,
             T_Q, S_KV, h_q, h_kv, D_HEAD,
             1, 1,                               # C=1, P=1 (no SP, degenerate)

tests/attention/test_gqa_decode_mc.py

@@ -31,7 +31,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from kernbench.benches._gqa_decode import gqa_decode_kernel  # noqa: F401
+from kernbench.benches._gqa_decode_long import gqa_decode_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
 from kernbench.policy.placement.dp import DPPolicy
@@ -82,7 +82,7 @@ def _run_decode_mc(*, h_q: int, h_kv: int, C: int, P: int, S_kv: int):
                       name=f"o_h{h_q}_kv{h_kv}_c{C}_p{P}")
         ctx.launch(
             f"gqa_decode_mc_h{h_q}_kv{h_kv}_c{C}_p{P}",
-            gqa_decode_kernel,
+            gqa_decode_long_kernel,
             q, k, v, o,
             T_Q, S_kv, h_q, h_kv, D_HEAD,
             C, P,

tests/attention/test_gqa_decode_sp.py

@@ -22,7 +22,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from kernbench.benches._gqa_decode import gqa_decode_kernel  # noqa: F401
+from kernbench.benches._gqa_decode_long import gqa_decode_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
 from kernbench.policy.placement.dp import DPPolicy
@@ -70,7 +70,7 @@ def _run_decode_sp(*, h_q: int, h_kv: int, P: int, S_kv: int):
                       dtype=DTYPE, dp=dp_full, name=f"o_h{h_q}_kv{h_kv}_p{P}")
         ctx.launch(
             f"gqa_decode_sp_h{h_q}_kv{h_kv}_p{P}",
-            gqa_decode_kernel,
+            gqa_decode_long_kernel,
             q, k, v, o,
             T_Q, S_kv, h_q, h_kv, D_HEAD,
             1, P,                                 # C=1, P=P (single-CUBE SP)

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_decode_long import gqa_decode_long_kernel  # noqa: F401
-from kernbench.benches._gqa_prefill import gqa_prefill_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,

tests/attention/test_gqa_prefill.py

@@ -1,6 +1,6 @@
 """Phase 1 spec test for P6a GQA prefill kernel (head-parallel, C=1 baseline).
 
-P6a introduces ``_gqa_prefill.py`` with the head-parallel structure (one
+P6a introduces ``_gqa_prefill_long.py`` with the head-parallel structure (one
 Q head per CUBE, per-CUBE distributed output, no reduce). C=1 is the
 degenerate case — no Ring KV, no IPCQ traffic. Validates kernel
 structure and T_q > 1 attention.
@@ -21,7 +21,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from kernbench.benches._gqa_prefill import gqa_prefill_kernel  # noqa: F401
+from kernbench.benches._gqa_prefill_long import gqa_prefill_long_kernel  # noqa: F401
 from kernbench.policy.placement.dp import DPPolicy
 from kernbench.runtime_api.bench_runner import run_bench
 from kernbench.runtime_api.types import resolve_device
@@ -62,7 +62,7 @@ def _run_prefill(*, T_q: int, S_kv: int, C: int = 1):
                       name=f"o_t{T_q}_c{C}")
         ctx.launch(
             f"gqa_prefill_p6a_t{T_q}_s{S_kv}_c{C}",
-            gqa_prefill_kernel,
+            gqa_prefill_long_kernel,
             q, k, v, o,
             T_q, S_kv, D_HEAD, C,
             _auto_dim_remap=False,

tests/attention/test_gqa_prefill_ring.py

@@ -34,7 +34,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from kernbench.benches._gqa_prefill import gqa_prefill_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_ring  # noqa: F401 (Phase 2)
 from kernbench.policy.placement.dp import DPPolicy
@@ -89,7 +89,7 @@ def _run_prefill_ring(*, T_q: int, S_kv: int, C: int):
                       name=f"o_t{T_q}_c{C}_ring")
         ctx.launch(
             f"gqa_prefill_ring_t{T_q}_s{S_kv}_c{C}",
-            gqa_prefill_kernel,
+            gqa_prefill_long_kernel,
             q, k, v, o,
             T_q, S_kv, D_HEAD, C,
             _auto_dim_remap=False,

tests/attention/test_gqa_scoped_writeback.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_decode_long import gqa_decode_long_kernel  # noqa: F401
-from kernbench.benches._gqa_prefill import gqa_prefill_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,
@@ -79,7 +79,7 @@ def _run_decode_sp(*, h_q: int, h_kv: int, P: int, S_kv: int):
                       dtype=DTYPE, dp=dp_full, name=f"o_sc_{P}")
         ctx.launch(
             f"gqa_decode_scoped_{P}",
-            gqa_decode_kernel,
+            gqa_decode_long_kernel,
             q, k, v, o,
             1, S_kv, h_q, h_kv, D_HEAD,
             1, P,
@@ -138,7 +138,7 @@ def _run_prefill_ring(*, T_q: int, S_kv: int, C: int):
                       dtype=DTYPE, dp=dp_o, name=f"o_ring_{C}")
         ctx.launch(
             f"gqa_prefill_scoped_{C}",
-            gqa_prefill_kernel,
+            gqa_prefill_long_kernel,
             q, k, v, o,
             T_q, S_kv, D_HEAD, C,
             _auto_dim_remap=False,