kernels/cuda: paged-attention kernel, dispatch, pinned host memory

CUDA layer for the paged-KV + swap work:
- csrc: new paged_attention.cu plus updates across attention/gemm/norm/
  activation/embedding/reduce kernels and common.cuh.
- xserv-kernels: new dispatch module and kernel-binding updates.
- xserv-cuda: cudaMallocHost/FreeHost bindings + PinnedBuffer (host swap
  pool backing) and offset-aware D2H/H2D copies used to move KV blocks
  between the GPU pool and pinned host memory.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

csrc/attention/flash_attention.cu

@@ -1,5 +1,6 @@
 #include <cuda_bf16.h>
 #include <float.h>
+#include "../common.cuh"
 
 // Flash Attention 2 forward kernel for BF16 with FP32 accumulation.
 //
@@ -391,6 +392,7 @@ void launch_flash_attention_bf16(
         q_len, kv_len, head_dim,
         scale, causal
     );
+    CUDA_CHECK_LAST_ERROR();
 }
 
 void launch_decode_attention_bf16(
@@ -411,6 +413,7 @@ void launch_decode_attention_bf16(
         kv_len, head_dim,
         scale
     );
+    CUDA_CHECK_LAST_ERROR();
 }
 
 }