Bundle sparse_sage Triton kernel for block-sparse attention

Without sparse attention, the model uses full (dense) attention which
attends to distant irrelevant information, causing ghosting artifacts.
The FlashVSR paper explicitly requires block-sparse attention.

Vendored from SageAttention team (Apache 2.0), pure Triton (no CUDA C++).
Import chain: local sparse_sage → external sageattn.core → SDPA fallback.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

flashvsr_arch/models/sparse_sage/__init__.py

@@ -0,0 +1,3 @@
+from .core import sparse_sageattn
+
+__all__ = ["sparse_sageattn"]