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>

crates/xserv-kernels/src/gemm.rs

@@ -20,7 +20,7 @@ unsafe extern "C" {
 }
 
 // --- FFI: cuBLAS ---
-type CublasHandle = *mut c_void;
+pub type CublasHandle = *mut c_void;
 
 #[allow(non_upper_case_globals)]
 const CUBLAS_OP_N: i32 = 0;
@@ -100,6 +100,13 @@ where
     })
 }
 
+/// Get the thread-local cuBLAS handle for use with dispatch module.
+pub fn cublas_handle() -> CublasHandle {
+    CUBLAS_CTX.with(|cell| {
+        cell.borrow().handle
+    })
+}
+
 /// Matrix multiplication: C = A @ B
 /// A: [M, K], B: [K, N], C: [M, N]
 /// All tensors must be contiguous and on the same GPU.