policy: add DPPolicy.cube_start for disjoint cube sub-meshes within a SIP

Adds an optional ``cube_start: int = 0`` field to ``DPPolicy``. In
``resolve_dp_policy`` the generated ``ShardSpec.cube`` is now
``policy.cube_start + cube_id`` instead of just ``cube_id``. With the
default value (0) every existing call site resolves to identical
``ShardSpec.cube`` values (cubes 0..num_cubes-1).

Why this is needed: the GQA Llama-70B 8-KV-group headline target lays
two 2x4 KV-groups per SIP — the first on cubes 0..7 (rows 0..1), the
second on cubes 8..15 (rows 2..3). Without ``cube_start``, ``DPPolicy``
can only address the first 8 row-major cubes, so a second launch on
the same SIP overlaps the first. ``cube_start=8`` selects the second
2x4 sub-mesh directly.

Design choice: scalar ``cube_start`` (vs a 2D ``cube_mesh_origin`` or
arbitrary ``cube_ids`` list) was picked because (a) the 2D mesh-mlo
kernel already assumes row-major contiguous cubes, (b) it pairs
naturally with ``num_cubes`` (range = ``[start, start+count)``), and
(c) zero migration churn — every existing call site stays unchanged.

Scope: 5 production LOC (one field + one expression in resolve). No
kernel changes here; kernels that consume ``program_id(axis=1)`` for
ring arithmetic need their own follow-up (see ADR-0022 contract).

Tests: 7 new unit tests in ``test_dppolicy_cube_start.py`` covering
default behavior preservation (cube_start=0), shifted ranges
(cube_start=8 → cubes 8..15), full-SIP CCL pattern, replicate cube
policy, shard-count preservation, and uniqueness. ADR-0026 regression
suite (12 tests) stays green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/kernbench/policy/placement/dp.py

@@ -33,12 +33,20 @@ class DPPolicy:
     Optional overrides (``None`` = use topology dimensions):
       - num_pes: override PEs per cube
       - num_cubes: override cubes per SIP
+
+    Cube range:
+      - cube_start: index of the first cube in the SIP to place shards
+        on. Defaults to 0. Enables disjoint sub-meshes within one SIP
+        (e.g. cubes 8..15 alongside cubes 0..7) — required by the
+        GQA Llama-70B 8-KV-group headline target (two 2×4 KV-groups
+        per SIP).
     """
 
     cube: Literal["replicate", "column_wise", "row_wise"] = "replicate"
     pe: Literal["replicate", "column_wise", "row_wise"] = "replicate"
     num_pes: int | None = None
     num_cubes: int | None = None
+    cube_start: int = 0
 
 
 @dataclass(frozen=True)
@@ -125,7 +133,7 @@ def resolve_dp_policy(
         for ls in local_shards:
             all_shards.append(ShardSpec(
                 sip=target_sip,
-                cube=cube_id,
+                cube=policy.cube_start + cube_id,
                 pe=ls.local_pe,
                 offset_bytes=cube_offset + ls.offset_bytes,
                 nbytes=ls.nbytes,