feat: unify attention backend with multi-dim mask support

- Add attention() functional entry delegating to active backend
- GQA/MLA forward calls attention() instead of inline cache/SDPA
- CUDA kernels support 2D/3D/4D mask via mask_h_stride field
- CudaBackend.fwd_decode builds 2D padding mask for mixed seq_lens
- KVCache.max_len precomputed in bind_tasks to avoid GPU sync
- batch==1 decode short-circuits mask=None
- Split tests into conftest, test_backend, test_backend_equivalence, test_kernel_mask
- 440 tests pass, L20 decode 1.44-1.60x speedup vs torch native

astrai/model/components/__init__.py

@@ -1,4 +1,4 @@
-from astrai.model.components.attention import GQA, MLA, repeat_kv
+from astrai.model.components.attention import GQA, MLA
 from astrai.model.components.decoder_block import DecoderBlock
 from astrai.model.components.embedding import Embedding
 from astrai.model.components.linear import Linear
@@ -21,5 +21,4 @@ __all__ = [
     "RotaryEmbedding",
     "apply_rotary_emb",
     "get_rotary_emb",
-    "repeat_kv",
 ]