phase 14: Flash Attention 2 for SM120 (RTX 5090)

Implement Flash Attention 2 forward kernel targeting SM120 (CC 12.0).
FA4 requires TMEM (only on data-center Blackwell SM100), so FA2 is the
correct target for consumer Blackwell GPUs like the RTX 5090.

CUDA kernel (csrc/attention/flash_attention.cu):
- Online softmax with tiled Q/K/V — O(1) extra memory, no S×S matrix
- Tile sizes: BR=BC=64, head_dim up to 128 (runtime parameter)
- BF16 input, FP32 accumulation, BF16 output
- Native GQA: kv_head = q_head / (num_q_heads / num_kv_heads)
- Causal mask with tile-level skip optimization
- Shared memory: 32 KB (Q_tile 16KB + KV_tile 16KB, fits in 48KB default)
- Grid: (q_tiles, batch × num_q_heads), Block: 128 threads

Integration:
- flash_attention() Rust wrapper in xserv-kernels with shape/dtype validation
- Qwen3 forward_gpu_cache uses flash_attention directly (no repeat_kv_gpu)
- Eliminates repeat_kv memory allocation + copy per layer per step
- Naive attention() preserved for testing/comparison

Validated on dash5 (RTX 5090, CUDA 12.9):
- Correctness: 9/10 top-1 match vs HF (identical to pre-FA baseline)
- Throughput: 12.9 tok/s (up from 10.3, +25% improvement)
- Now at 35% of HF transformers baseline (up from 30%)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/xserv-kernels/src/lib.rs

@@ -10,7 +10,7 @@ pub mod transpose;
 
 pub use activation::{add, gelu, mul, scale, silu};
 pub use transpose::{merge_heads_gpu, repeat_kv_gpu, reshape_heads_gpu, strided_to_contiguous_gpu, transpose_for_rope_gpu, transpose_from_rope_gpu};
-pub use attention::attention;
+pub use attention::{attention, flash_attention};
 pub use embedding::embedding;
 pub use gemm::{batched_matmul, matmul, GemmBackend};
 pub use layernorm::layernorm;