feat(dispatcher): add has_backend_impl and expose op name on dispatch wrapper & other updates

[hannahli-nv]

Description

Update codes.

This PR contains 6 new commit(s).

Commits included:

15b2869 fix(tilecpp): mask the FMHA forward tail store
e2fb207 fix(cutile): MLA split-KV NaN on sm_80 for non-power-of-2 seqlen
303cb2b cuTile ragged_bmm: tune both kernel variants instead of guessing swap_ab from the shape
aafefca fix(tilecpp): chunk_gated_delta_rule V-tile bounds and G/Beta dtype
1f622f6 perf(cutile softmax): per-op approx exp/div in all forward kernels
015412f feat(dispatcher): add has_backend_impl and expose op name on dispatch wrapper

CI Configuration

config:
  build: true
  # valid options are "ops" and "benchmark"
  test: []

Checklist

• Code formatted and imports sorted via repo specifications (./format.sh)
• Documentation updated (if needed)
• CI configuration reviewed

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[hannahli-nv]

/ok to test 8a72068